Articulated Tracking with a Dynamic High-Resolution Surface Model
|
|
- Penelope Robbins
- 5 years ago
- Views:
Transcription
1 Articulated Tracking with a Dynamic High-Resolution Surface Model Aaron Walsman Tanner Schmidt Dieter Fox Paul G. Allen School of Computer Science and Engineering University of Washington {awalsman, tws10, fox@cs.washington.edu I. I NTRODUCTION In order for robots to interact with complex deformable objects, a vision system must produce a perceptual representation that combines both spatial and semantic information, and must be fast enough to keep up with the object s physical motion. This is especially true of systems that interact directly with humans where safety is critical and mistakes can be dangerous. We present a real-time system that tracks the surface and kinematic pose of deformable objects using a model-based optimization. Our primary goal is to provide accurate surface estimation that not only adapts to match a particular subject, but does so dynamically, tracking complex surface details such as folds and wrinkles as they appear and disappear. Our approach fits a skeletal model and high-resolution polygon mesh to a point cloud. The skeleton is designed to capture the underlying kinematic structure of the subject and estimate it s large-scale motion, while the polygon mesh captures volume differences between subjects and more complex surface details. This gives a robotic system both a lowdimensional pose that can be used for gesture and activity recognition, as well as a dense surface estimate which can be used for precise physical interaction. Furthermore, because our mesh comes from a predefined template, it is semantically consistent across capture sessions with different subjects. This means that we can tell not only where the surface of the subject is, but which regions of this surface correspond to different body parts. Our skeleton fitting approach is similar to other generative methods for articulated model tracking [3, 9, 10, 12, 20, 23]. This requires model initialization, but means that we can easily track new subject types as long as an appropriate template model is available. This also means we can avoid the expensive data collection efforts required by approaches with a discriminative component [8, 13, 19, 22, 21]. Our surface fitting technique was inspired by dynamic surface reconstruction methods [7, 14, 17]. These use reconstruction techniques such as volumetric SDF fusion [5] while simultaneously estimating deformation parameters that warp the surface into place. Rather than build a new mesh for each capture session, we instead use a template model that is attached to the kinematic skeleton using traditional smooth binding approaches from computer graphics [15] and further deform it to fit an observed point cloud. The motivating applications behind our work are robotic Fig. 1. Our model tracking a point cloud. Top left: Colored point cloud input. Top Right: Estimated skeleton and surface mesh without surface tracking. Bottom Left: High resolution mesh tracking the dynamic shape of the subject. Bottom Right: The high resolution mesh with projected colors. tasks that require precise spatial information about humans and deformable objects. There are several robotics applications in personal assistance, health care and rehabilitation that are hampered by a lack of reliable human pose and surface estimation. In addition to robotics, this approach has further applications in augmented reality, performance capture and interactive games. II. T EMPLATE M ODEL Similar to Ye and Yang [23] and Schmidt et al. [20] our technique uses an iterative gradient-based approach to fit a kinematics model to observed data. We assume that the tracking sequence starts with an initial estimate of the skeletal pose. From that initialization, we iteratively optimize the pose to fit each incoming frame. We then use a second optimization to update the vertex positions of a triangle mesh representing the object s surface.
2 A. Dual Quaternion Kinematics Our model consists of a kinematic skeleton with an attached mesh. The skeleton forms a tree of rigid link frames connected by flexible joints. Each link has a position and orientation represented as a transformation in 3D space relative to the camera. We use dual quaternions [4] to parameterize this space of rigid transformations SE(3). For the sake of space, we omit a thorough coverage of the mathematical details and instead refer readers to [6]. We use single axis hinge and prismatic joints to describe the offset between frames meaning that the pose of each joint can be described by a single parameter θ j. For joints with multiple degrees of freedom such as the shoulder or wrist, we use multiple overlapping joints. The pose of the entire skeleton can be described as a single vector Θ containing all of these joint parameters. B. Surface Representation and Binding The model s surface is represented as a high resolution triangle mesh. This consists of set of 3D vertex positions V = { v 1... v V, vi R 3 as well as a triangle list F. Each triangle is represented as a set of three integers referencing vertex indices F = { f 1... f F, fk Z 3. The mesh is attached to the skeleton using dual quaternion binding [15] which provides a way to smoothly blend the influence of links between different regions of the mesh. This technique is also used by Dynamic Fusion [17] to attach the reconstructed mesh to a set of warp node transforms. Dual quaternion binding requires a bind pose dual quaternion Hj 0 for each link in the skeleton as well as a weight matrix Ω describing the influence of each frame on each vertex. The bind pose represents the pose for which the kinematic skeleton matches the default pose of the mesh. Each column ω i corresponding to vertex i is constrained to sum to one. Given this information the binding function transforms a vertex by computing the offset between the bind pose and the current pose H j of each frame and then constructing a linear blend H iσ of these offsets for each vertex v i based on the weights. H iσ = ( ) H j H 0 1 j ωij (1) j The skinned vertex position v i can be computed by multiplying this transformation by the vertex position in the default model v 0 i. v i = H iσ v 0 i (2) Our human mesh originated from a model from on the website CG Trader [2] by the NoneCG group [18] and used with permission. We heavily modified this mesh and constructed the skeleton hierarchy and skin weights weights using Autodesk s Maya software [1]. C. Dynamic Shape Parameters Dynamic shape warping is represented by a set of offsets Φ containing a three vector φ i R 3 for each vertex describing a translation away from its default position. We can augment Equation 2 above to compute the warped position v i : v i = H iσ (v 0 i + φ i ) (3) III. OPTIMIZATION Using this model, we formulate pose and shape tracking as a damped-least-squares optimization process. We will first discuss our data association and residual computation before going into more detail on the kinematic and shape optimization steps. A. Data Association and Residual Given the model described in Section II the task of estimating pose and shape requires estimating the joint angles Θ and the vertex offsets Φ. This is achieved by first generating a residual term describing the distance between the model and the observations, computing the derivative of that residual with respect to the parameters Θ and Φ and then using an optimization step to compute an offset to these parameters that reduces the error. Our observations take the form of a point cloud P = { p1... p P, pk R 3. The error term is computed by first constructing an assignment between vertices and observations. The data assignment is computed bidirectionally by finding the closest observation for each vertex and the closest vertex for each observation. Schmidt et al. [20] have shown that this improves robustness in certain conditions. Once we have the assignment we compute a point-plane error term [3] for each vertex based on these sources. If we let N = { n 1... n V be the vertex normals, P = { p1... p V be the closest observed point to each vertex and P = { p 1... p V be the average of the observation points for which each vertex in V is the closest, we can construct the residual for each vertex as r i = n T i (λ a ( p i v i ) + (1 λ a )( p i v i )) (4) B. Kinematic Optimization The residual in equation 4 a function of the vertex positions V. The position of each vertex is a function of the skeleton pose Θ, the bind pose H 0, the default mesh vertices V 0, the vertex offsets Φ and the skin weights Ω. Therefore, we use the chain rule to compute the Jacobian of this residual J r = r/ Θ as a product of two partial derivatives. This means that each row J ri of J r corresponding to vertex i can be written as: J ri = r i Θ = r i V V Θ Because we use point-plane error, the derivative of the residual with respect to the vertex position is the vertex normal. The derivative of the vertex position with respect to the skeleton pose Θ is more complex, but can be computed analytically. Due to space, we omit the details of the full derivative here. In addition to the per-vertex residual in equation 4 we add a residual per joint that encourages the skeleton to move towards its default pose. This takes the form r j = s j θ j where s j is a scalar that depends on the number of vertices affected by each joint. We construct the Jacobian J k for the full kinematics by concatenating the vertex residual J r with the the Jacobian of the pose prior which has rows of the form J θi = r j / Θ.
3 [ ] Jr J k = J θ We then use damped least-squares [16] to solve for a pose offset Θ. (J T J + λ d1 diag(j T J)) Θ = J T r The (J T J + λ d1 diag(j T J)) matrix is positive definite, meaning it can be solved efficiently using Cholesky decomposition [11]. Once Θ has been computed it is subtracted from the current pose Θ and the process is repeated. In practice we have found that ten to fifteen iterations of this optimization for each incoming frame is sufficient to match the pose of the target. The top right frame of Figure 1 shows the result of fitting the kinematic model with the default mesh onto a point cloud. C. Shape Optimization Once the pose has been fit, we update the shape deformation parameters Φ. These consist of a three vector φ i for each vertex. The shape optimization uses the residual from Equation 4 but incorporates additional regularization terms. r φi = r i + λ s φ i λ n φ i φ n 2 2 (5) n N (i) The first regularization term, weighted by λ s, penalizes the magnitude of the φ i deformation vector. This helps prevent the mesh from drifting off the skeleton. The second regularization term penalizes the difference between each vertex offset and those of its neighboring vertices which helps prevent surface discontinuities and creases. As before we compute the derivative of this residual with respect to each parameter of Φ, but make one important simplifying approximation. Technically the second regularization term introduces interdependence between each φ i and its neighbors, but in order to simplify the computation we treat each φ i as if it were independent. This means that instead of solving one large but sparse 3 V by 3 V linear system we can break it up into a separate 3 by 3 linear systems for each vertex and solve them in parallel. This means we compute a Jacobian J φi for each vertex as J φi = r φ i φ i = r i φ i + 2λ s φ i + 2λ n n N (i) (φ i φ n ) Fig. 3. Our performance on the EVAL dataset compared to Articulated ICP reported by [9], Ganapthi et al.[9], Schmidt et al.[20] and Ye and Yang[23]. Once we have computed our Jacobian J φi we use damped least squares as before and solve (J T φ i J φi + λ d2 diag(j T φ i J φi )) φi = J T i r φi for φi, and subtract it from φ i. The bottom left frame of Figure 1 shows the result of the shape deformation after the kinematic pose has been fit. In practice only two iterations of shape refinement are necessary for each incoming video frame. IV. EXPERIMENTS There are a number of existing datasets designed to test the capabilities of markerless motion capture systems, but to our knowledge there are no existing benchmarks for evaluating both pose and high resolution dynamic shape estimation simultaneously. We therefore evaluate our pose tracking on the EVAL dataset [9] without dynamic shape warping and do further experiments with our own data to quantify the performance of our mesh tracking. A. EVAL Dataset The EVAL dataset consists of twenty four RGBD sequences split evenly across three human subjects with varying body proportions. We use the standard evaluation criteria which is the percentage of frames in which the estimated joint position is within ten centimeters of the ground truth. Because the ground truth data relies on joint locations specific to a Fig. 2. Histograms of the distance from forward-facing vertices to their closest observation point computed over all frames for each of sixteen sequences. Here the results have been combined based on the distance from the camera. The x axis is from 0 to five centimeters binned to half-millimeter intervals, while the y axis is the percentage of vertices with a distance that falls into that range. Eighty percent of points have a value less than the dashed lines.
4 Fig. 5. The point cloud is shown on the left. The center shows the mesh with no dynamic shape warping (Φ = 0). The fully deformed mesh is shown on the right. The center and right are colored to show distance to the closest point in the point cloud. particular model, we follow the technique of [23] and use mean-subtraction to find the best placement of the tracked joints relative to our model. Figure 3 shows our performance compared to the reported scores of other methods. While we do not perform as well as other state of the art techniques, our method was not designed to work with low resolution depth data and our results are comparable with the range of existing literature. B. Shape Fitting Experiments In order to test our shape estimation we generated a new dataset consisting of sixteeen high resolution RGBD sequences. These sequences were captured from four subjects at three different distances and feature basic motion such as waves, stretches, pointing and hand overs. These sequences also include data from three different distances: head and shoulders, upper torso and full body. To show the degree to which our shape optimization improves surface fitting, we tracked our model through each sequence twice. For one run the track is run normally but for the other the vertex offsets are disabled so that the model maintains its default shape throughout the sequence. For each run we record the distance from each visible model vertex to its closest observation point in each frame. Because we do not have dense ground truth labels for this data, these results do not show overall tracking performance. Instead this data shows how much the dynamic shape estimation improves fitting the point-cloud observations. Figure 2 shows these errors binned into histograms while Figure 5 shows one frame with both meshes colored to indicate this error. The shape estimation shows improvement in the form of higher concentration of error at low values for all sequences. However this improvement is most pronounced at closer ranges where more detail is visible. C. Qualitative Results Figure 4 shows several colored point clouds and their corresponding tracked meshes at varying distances from the camera. In all cases the tracker was given a rough initialization of the subject s pose at the start of the sequence, and the pose and shape tracked from that point forward. V. CONCLUSION We have demonstrated an approach for tracking deformable articulated objects using model-based optimization and shown that it can produce dense and accurate estimation of detailed deforming surfaces in real time. This system also provides useful pose estimates of the model s kinematic structure for gesture recognition and motion prediction. Fig. 4. A collection of still frames showing the results of our system. For each pair of images, the left shows the colored point cloud while the right shows our warped output mesh.
5 REFERENCES [1] Autodesk Incorporated. Maya. URL com/products/maya/overview. [2] CG Trader. Cg trader. URL [3] Yang Chen and Gérard Medioni. Object modelling by registration of multiple range images. Image and vision computing, 10(3): , [4] William Kingdon Clifford. Mathematical papers. Macmillan and Company, [5] Brian Curless and Marc Levoy. A volumetric method for building complex models from range images. In Proceedings of the 23rd annual conference on Computer graphics and interactive techniques, pages ACM, [6] Konstantinos Daniilidis. Hand-eye calibration using dual quaternions. The International Journal of Robotics Research, 18(3): , [7] Mingsong Dou, Sameh Khamis, Yury Degtyarev, Philip Davidson, Sean Ryan Fanello, Adarsh Kowdle, Sergio Orts Escolano, Christoph Rhemann, David Kim, Jonathan Taylor, et al. Fusion4d: Real-time performance capture of challenging scenes. ACM Transactions on Graphics (TOG), 35(4):114, [8] Varun Ganapathi, Christian Plagemann, Daphne Koller, and Sebastian Thrun. Real time motion capture using a single time-of-flight camera. In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, pages IEEE, [9] Varun Ganapathi, Christian Plagemann, Daphne Koller, and Sebastian Thrun. Real-time human pose tracking from range data. In European conference on computer vision, pages Springer, [10] Cristina Garcia Cifuentes, Jan Issac, Manuel Wüthrich, Stefan Schaal, and Jeannette Bohg. Probabilistic articulated real-time tracking for robot manipulation. IEEE Robotics and Automation Letters (RA-L), [11] Philip E Gill and Walter Murray. Newton-type methods for unconstrained and linearly constrained optimization. Mathematical Programming, 7(1): , [12] Daniel Grest, Jan Woetzel, and Reinhard Koch. Nonlinear body pose estimation from depth images. In Joint Pattern Recognition Symposium, pages Springer, [13] Thomas Helten, Andreas Baak, Gaurav Bharaj, Meinard Müller, Hans-Peter Seidel, and Christian Theobalt. Personalization and evaluation of a real-time depth-based full body tracker. In 2013 International Conference on 3D Vision-3DV 2013, pages IEEE, [14] Matthias Innmann, Michael Zollhöfer, Matthias Nießner, Christian Theobalt, and Marc Stamminger. Volumedeform: Real-time volumetric non-rigid reconstruction. In Proceedings of the European Conference on Computer Vision (ECCV), [15] Ladislav Kavan, Steven Collins, Jiří Žára, and Carol O Sullivan. Geometric skinning with approximate dual quaternion blending. ACM Transactions on Graphics (TOG), 27(4):105, [16] Donald W Marquardt. An algorithm for least-squares estimation of nonlinear parameters. Journal of the society for Industrial and Applied Mathematics, 11(2): , [17] Richard A Newcombe, Dieter Fox, and Steven M Seitz. Dynamicfusion: Reconstruction and tracking of nonrigid scenes in real-time. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages , [18] NoneCG. Nonecg. URL [19] Christian Plagemann, Varun Ganapathi, Daphne Koller, and Sebastian Thrun. Real-time identification and localization of body parts from depth images. In Robotics and Automation (ICRA), 2010 IEEE International Conference on, pages IEEE, [20] Tanner Schmidt, Richard Newcombe, and Dieter Fox. Dart: Dense articulated real-time tracking. Proceedings of Robotics: Science and Systems, Berkeley, USA, 2, [21] Jamie Shotton, Toby Sharp, Alex Kipman, Andrew Fitzgibbon, Mark Finocchio, Andrew Blake, Mat Cook, and Richard Moore. Real-time human pose recognition in parts from single depth images. Communications of the ACM, 56(1): , [22] Jonathan Tompson, Murphy Stein, Yann Lecun, and Ken Perlin. Real-time continuous pose recovery of human hands using convolutional networks. ACM Transactions on Graphics (TOG), 33(5):169, [23] Mao Ye and Ruigang Yang. Real-time simultaneous pose and shape estimation for articulated objects using a single depth camera. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages , 2014.
Dynamic High Resolution Deformable Articulated Tracking
Dynamic High Resolution Deformable Articulated Tracking Aaron Walsman Weilin Wan awalsman@cs.washington.edu weiliw@uw.edu Tanner Schmidt tws10@cs.washington.edu Dieter Fox fox@cs.washington.edu Paul G.
More informationIntrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting
Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting R. Maier 1,2, K. Kim 1, D. Cremers 2, J. Kautz 1, M. Nießner 2,3 Fusion Ours 1
More informationMonocular Tracking and Reconstruction in Non-Rigid Environments
Monocular Tracking and Reconstruction in Non-Rigid Environments Kick-Off Presentation, M.Sc. Thesis Supervisors: Federico Tombari, Ph.D; Benjamin Busam, M.Sc. Patrick Ruhkamp 13.01.2017 Introduction Motivation:
More informationGeometric Reconstruction Dense reconstruction of scene geometry
Lecture 5. Dense Reconstruction and Tracking with Real-Time Applications Part 2: Geometric Reconstruction Dr Richard Newcombe and Dr Steven Lovegrove Slide content developed from: [Newcombe, Dense Visual
More informationNon-rigid Reconstruction with a Single Moving RGB-D Camera
Non-rigid Reconstruction with a Single Moving RGB-D Camera Shafeeq Elanattil 1,2, Peyman Moghadam 1,2, Sridha Sridharan 2, Clinton Fookes 2, Mark Cox 1 1 Autonomous Systems Laboratory, CSIRO Data61, Brisbane,
More informationReal-Time Human Pose Recognition in Parts from Single Depth Images
Real-Time Human Pose Recognition in Parts from Single Depth Images Jamie Shotton, Andrew Fitzgibbon, Mat Cook, Toby Sharp, Mark Finocchio, Richard Moore, Alex Kipman, Andrew Blake CVPR 2011 PRESENTER:
More informationAccurate 3D Face and Body Modeling from a Single Fixed Kinect
Accurate 3D Face and Body Modeling from a Single Fixed Kinect Ruizhe Wang*, Matthias Hernandez*, Jongmoo Choi, Gérard Medioni Computer Vision Lab, IRIS University of Southern California Abstract In this
More informationPose Estimation on Depth Images with Convolutional Neural Network
Pose Estimation on Depth Images with Convolutional Neural Network Jingwei Huang Stanford University jingweih@stanford.edu David Altamar Stanford University daltamar@stanford.edu Abstract In this paper
More informationArticulated Gaussian Kernel Correlation for Human Pose Estimation
Articulated Gaussian Kernel Correlation for Human Pose Estimation Meng Ding and Guoliang Fan School of Electrical and Computer Engineering, Oklahoma State University, Stillwater, OK, USA 74074 meng.ding@okstate.edu;
More informationTri-modal Human Body Segmentation
Tri-modal Human Body Segmentation Master of Science Thesis Cristina Palmero Cantariño Advisor: Sergio Escalera Guerrero February 6, 2014 Outline 1 Introduction 2 Tri-modal dataset 3 Proposed baseline 4
More informationSCAPE: Shape Completion and Animation of People
SCAPE: Shape Completion and Animation of People By Dragomir Anguelov, Praveen Srinivasan, Daphne Koller, Sebastian Thrun, Jim Rodgers, James Davis From SIGGRAPH 2005 Presentation for CS468 by Emilio Antúnez
More informationKey Developments in Human Pose Estimation for Kinect
Key Developments in Human Pose Estimation for Kinect Pushmeet Kohli and Jamie Shotton Abstract The last few years have seen a surge in the development of natural user interfaces. These interfaces do not
More informationColored Point Cloud Registration Revisited Supplementary Material
Colored Point Cloud Registration Revisited Supplementary Material Jaesik Park Qian-Yi Zhou Vladlen Koltun Intel Labs A. RGB-D Image Alignment Section introduced a joint photometric and geometric objective
More informationCOLLABORATIVE VOTING OF 3D FEATURES FOR ROBUST GESTURE ESTIMATION. Daniel van Sabben, Javier Ruiz-Hidalgo, Xavier Suau Cuadros, Josep R.
COLLABORATIVE VOTING OF 3D FEATURES FOR ROBUST GESTURE ESTIMATION Daniel van Sabben, Javier Ruiz-Hidalgo, Xavier Suau Cuadros, Josep R. Casas Universitat Politècnica de Catalunya Image Processing Group
More informationJamie Shotton, Andrew Fitzgibbon, Mat Cook, Toby Sharp, Mark Finocchio, Richard Moore, Alex Kipman, Andrew Blake CVPR 2011
Jamie Shotton, Andrew Fitzgibbon, Mat Cook, Toby Sharp, Mark Finocchio, Richard Moore, Alex Kipman, Andrew Blake CVPR 2011 Auto-initialize a tracking algorithm & recover from failures All human poses,
More informationPersonalization and Evaluation of a Real-time Depth-based Full Body Tracker
Personalization and Evaluation of a Real-time Depth-based Full Body Tracker Thomas Helten 1 Andreas Baak 1 Gaurav Bharaj 2 Meinard Müller 3 Hans-Peter Seidel 1 Christian Theobalt 1 1 MPI Informatik 2 Harvard
More informationRigging / Skinning. based on Taku Komura, Jehee Lee and Charles B.Own's slides
Rigging / Skinning based on Taku Komura, Jehee Lee and Charles B.Own's slides Skeletal Animation Victoria 2 CSE 872 Dr. Charles B. Owen Advanced Computer Graphics Skinning http://www.youtube.com/watch?
More informationSurface Reconstruction. Gianpaolo Palma
Surface Reconstruction Gianpaolo Palma Surface reconstruction Input Point cloud With or without normals Examples: multi-view stereo, union of range scan vertices Range scans Each scan is a triangular mesh
More informationObject Reconstruction
B. Scholz Object Reconstruction 1 / 39 MIN-Fakultät Fachbereich Informatik Object Reconstruction Benjamin Scholz Universität Hamburg Fakultät für Mathematik, Informatik und Naturwissenschaften Fachbereich
More informationIntroduction to Computer Graphics. Animation (1) May 19, 2016 Kenshi Takayama
Introduction to Computer Graphics Animation (1) May 19, 2016 Kenshi Takayama Skeleton-based animation Simple Intuitive Low comp. cost https://www.youtube.com/watch?v=dsonab58qva 2 Representing a pose using
More informationArticulated Pose Estimation with Flexible Mixtures-of-Parts
Articulated Pose Estimation with Flexible Mixtures-of-Parts PRESENTATION: JESSE DAVIS CS 3710 VISUAL RECOGNITION Outline Modeling Special Cases Inferences Learning Experiments Problem and Relevance Problem:
More informationCharacter animation Christian Miller CS Fall 2011
Character animation Christian Miller CS 354 - Fall 2011 Exam 2 grades Avg = 74.4, std. dev. = 14.4, min = 42, max = 99 Characters Everything is important in an animation But people are especially sensitive
More informationarxiv: v3 [cs.cv] 10 Jan 2018
HAND SEGMENTATION FOR HAND-OBJECT INTERACTION FROM DEPTH MAP Byeongkeun Kang Kar-Han Tan Nan Jiang Hung-Shuo Tai Daniel Tretter Truong Nguyen Department of Electrical and Computer Engineering, UC San Diego,
More informationA Model-based Approach to Rapid Estimation of Body Shape and Postures Using Low-Cost Depth Cameras
A Model-based Approach to Rapid Estimation of Body Shape and Postures Using Low-Cost Depth Cameras Abstract Byoung-Keon D. PARK*, Matthew P. REED University of Michigan, Transportation Research Institute,
More informationAdvanced Computer Graphics
G22.2274 001, Fall 2009 Advanced Computer Graphics Project details and tools 1 Project Topics Computer Animation Geometric Modeling Computational Photography Image processing 2 Optimization All projects
More informationArticulatedFusion: Real-time Reconstruction of Motion, Geometry and Segmentation Using a Single Depth Camera
ArticulatedFusion: Real-time Reconstruction of Motion, Geometry and Segmentation Using a Single Depth Camera Chao Li, Zheheng Zhao, and Xiaohu Guo Department of Computer Science, The University of Texas
More informationData-driven Depth Inference from a Single Still Image
Data-driven Depth Inference from a Single Still Image Kyunghee Kim Computer Science Department Stanford University kyunghee.kim@stanford.edu Abstract Given an indoor image, how to recover its depth information
More informationMobile Point Fusion. Real-time 3d surface reconstruction out of depth images on a mobile platform
Mobile Point Fusion Real-time 3d surface reconstruction out of depth images on a mobile platform Aaron Wetzler Presenting: Daniel Ben-Hoda Supervisors: Prof. Ron Kimmel Gal Kamar Yaron Honen Supported
More information3D Reconstruction with Tango. Ivan Dryanovski, Google Inc.
3D Reconstruction with Tango Ivan Dryanovski, Google Inc. Contents Problem statement and motivation The Tango SDK 3D reconstruction - data structures & algorithms Applications Developer tools Problem formulation
More informationStructured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov
Structured Light II Johannes Köhler Johannes.koehler@dfki.de Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Introduction Previous lecture: Structured Light I Active Scanning Camera/emitter
More informationA novel approach to motion tracking with wearable sensors based on Probabilistic Graphical Models
A novel approach to motion tracking with wearable sensors based on Probabilistic Graphical Models Emanuele Ruffaldi Lorenzo Peppoloni Alessandro Filippeschi Carlo Alberto Avizzano 2014 IEEE International
More information3D Computer Vision. Structured Light II. Prof. Didier Stricker. Kaiserlautern University.
3D Computer Vision Structured Light II Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 Introduction
More informationPoster Spotlights. Session: Motion and Tracking I: Tracking People, Tue 14 June 2010, 1:40-3:20 pm
The Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition Poster Spotlights Session: Motion and Tracking I: Tracking People, Tue 14 June 2010, 1:40-3:20 pm Efficient Extraction of Human
More informationCS Decision Trees / Random Forests
CS548 2015 Decision Trees / Random Forests Showcase by: Lily Amadeo, Bir B Kafle, Suman Kumar Lama, Cody Olivier Showcase work by Jamie Shotton, Andrew Fitzgibbon, Richard Moore, Mat Cook, Alex Kipman,
More informationKeywords:Synthetic Data, IBR, Data Generation Tool. Abstract
Data Generation Toolkit for Image Based Rendering Algorithms V Vamsi Krishna, P J Narayanan Center for Visual Information Technology International Institute of Information Technology, Hyderabad, India
More informationAnimation. CS 4620 Lecture 33. Cornell CS4620 Fall Kavita Bala
Animation CS 4620 Lecture 33 Cornell CS4620 Fall 2015 1 Announcements Grading A5 (and A6) on Monday after TG 4621: one-on-one sessions with TA this Friday w/ prior instructor Steve Marschner 2 Quaternions
More informationTEXTURE OVERLAY ONTO NON-RIGID SURFACE USING COMMODITY DEPTH CAMERA
TEXTURE OVERLAY ONTO NON-RIGID SURFACE USING COMMODITY DEPTH CAMERA Tomoki Hayashi 1, Francois de Sorbier 1 and Hideo Saito 1 1 Graduate School of Science and Technology, Keio University, 3-14-1 Hiyoshi,
More informationAnimation of 3D surfaces.
Animation of 3D surfaces Motivations When character animation is controlled by skeleton set of hierarchical joints joints oriented by rotations the character shape still needs to be visible: visible =
More informationColour Segmentation-based Computation of Dense Optical Flow with Application to Video Object Segmentation
ÖGAI Journal 24/1 11 Colour Segmentation-based Computation of Dense Optical Flow with Application to Video Object Segmentation Michael Bleyer, Margrit Gelautz, Christoph Rhemann Vienna University of Technology
More information3D Shape Recovery of Deformable Soft-tissue with Computed Tomography and Depth Scan
3D Shape Recovery of Deformable Soft-tissue with Computed Tomography and Depth Scan Jingwei Song 1, Jun Wang 1,2, Liang Zhao 1, Shoudong Huang 1, Gamini Dissanayake 1 1. Centre for Autonomous Systems,
More informationRobust Articulated ICP for Real-Time Hand Tracking
Robust Articulated-ICP for Real-Time Hand Tracking Andrea Tagliasacchi* Sofien Bouaziz Matthias Schröder* Mario Botsch Anastasia Tkach Mark Pauly * equal contribution 1/36 Real-Time Tracking Setup Data
More informationReal-Time Human Pose Tracking from Range Data
Real-Time Human Pose Tracking from Range Data Varun Ganapathi 1,2, Christian Plagemann 1,2, Daphne Koller 1, and Sebastian Thrun 1,2 1 Stanford University, Computer Science Department, Stanford, CA, USA
More informationVideo based Animation Synthesis with the Essential Graph. Adnane Boukhayma, Edmond Boyer MORPHEO INRIA Grenoble Rhône-Alpes
Video based Animation Synthesis with the Essential Graph Adnane Boukhayma, Edmond Boyer MORPHEO INRIA Grenoble Rhône-Alpes Goal Given a set of 4D models, how to generate realistic motion from user specified
More informationSynthesizing Realistic Facial Expressions from Photographs
Synthesizing Realistic Facial Expressions from Photographs 1998 F. Pighin, J Hecker, D. Lischinskiy, R. Szeliskiz and D. H. Salesin University of Washington, The Hebrew University Microsoft Research 1
More informationProject Updates Short lecture Volumetric Modeling +2 papers
Volumetric Modeling Schedule (tentative) Feb 20 Feb 27 Mar 5 Introduction Lecture: Geometry, Camera Model, Calibration Lecture: Features, Tracking/Matching Mar 12 Mar 19 Mar 26 Apr 2 Apr 9 Apr 16 Apr 23
More informationPatch-based Non-rigid 3D Reconstruction from a Single Depth Stream
Patch-based Non-rigid 3D Reconstruction from a Single Depth Stream Carmel Kozlov Miroslava Slavcheva Slobodan Ilic Technische Universität München Siemens Corporate Technology Abstract We propose an approach
More informationSurface Registration. Gianpaolo Palma
Surface Registration Gianpaolo Palma The problem 3D scanning generates multiple range images Each contain 3D points for different parts of the model in the local coordinates of the scanner Find a rigid
More informationAnimation of 3D surfaces
Animation of 3D surfaces 2013-14 Motivations When character animation is controlled by skeleton set of hierarchical joints joints oriented by rotations the character shape still needs to be visible: visible
More informationRobust Human Body Shape and Pose Tracking
Robust Human Body Shape and Pose Tracking Chun-Hao Huang 1 Edmond Boyer 2 Slobodan Ilic 1 1 Technische Universität München 2 INRIA Grenoble Rhône-Alpes Marker-based motion capture (mocap.) Adventages:
More informationGame Programming. Bing-Yu Chen National Taiwan University
Game Programming Bing-Yu Chen National Taiwan University Character Motion Hierarchical Modeling Character Animation Motion Editing 1 Hierarchical Modeling Connected primitives 2 3D Example: A robot arm
More informationMulti-view stereo. Many slides adapted from S. Seitz
Multi-view stereo Many slides adapted from S. Seitz Beyond two-view stereo The third eye can be used for verification Multiple-baseline stereo Pick a reference image, and slide the corresponding window
More informationMotion Capture & Simulation
Motion Capture & Simulation Motion Capture Character Reconstructions Joint Angles Need 3 points to compute a rigid body coordinate frame 1 st point gives 3D translation, 2 nd point gives 2 angles, 3 rd
More informationACQUIRING 3D models of deforming objects in real-life is
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 1 Robust Non-rigid Motion Tracking and Surface Reconstruction Using L 0 Regularization Kaiwen Guo, Feng Xu, Yangang Wang, Yebin Liu, Member, IEEE
More informationCS 775: Advanced Computer Graphics. Lecture 4: Skinning
CS 775: Advanced Computer Graphics Lecture 4: http://www.okino.com/conv/skinning.htm Binding Binding Always done in a standard rest or bind pose. Binding Always done in a standard rest or bind pose. Associate
More informationHuman body animation. Computer Animation. Human Body Animation. Skeletal Animation
Computer Animation Aitor Rovira March 2010 Human body animation Based on slides by Marco Gillies Human Body Animation Skeletal Animation Skeletal Animation (FK, IK) Motion Capture Motion Editing (retargeting,
More informationMarkerless Motion Capture with Multi-view Structured Light
Markerless Motion Capture with Multi-view Structured Light Ricardo R. Garcia, Avideh Zakhor; UC Berkeley; Berkeley, CA (a) (c) Figure 1: Using captured partial scans of (a) front and (b) back to generate
More informationHandSonor: A Customizable Vision-based Control Interface for Musical Expression
HandSonor: A Customizable Vision-based Control Interface for Musical Expression Srinath Sridhar MPI Informatik and Universita t des Saarlandes Campus E1.4, 66123 Saarbru cken, Germany ssridhar@mpi-inf.mpg.de
More informationMotion capture: An evaluation of Kinect V2 body tracking for upper limb motion analysis
Motion capture: An evaluation of Kinect V2 body tracking for upper limb motion analysis Silvio Giancola 1, Andrea Corti 1, Franco Molteni 2, Remo Sala 1 1 Vision Bricks Laboratory, Mechanical Departement,
More informationNIH Public Access Author Manuscript Proc Int Conf Image Proc. Author manuscript; available in PMC 2013 May 03.
NIH Public Access Author Manuscript Published in final edited form as: Proc Int Conf Image Proc. 2008 ; : 241 244. doi:10.1109/icip.2008.4711736. TRACKING THROUGH CHANGES IN SCALE Shawn Lankton 1, James
More informationGrasp Recognition using a 3D Articulated Model and Infrared Images
Grasp Recognition using a 3D Articulated Model and Infrared Images Koichi Ogawara Institute of Industrial Science, Univ. of Tokyo, Tokyo, Japan Jun Takamatsu Institute of Industrial Science, Univ. of Tokyo,
More informationSegmentation and Tracking of Partial Planar Templates
Segmentation and Tracking of Partial Planar Templates Abdelsalam Masoud William Hoff Colorado School of Mines Colorado School of Mines Golden, CO 800 Golden, CO 800 amasoud@mines.edu whoff@mines.edu Abstract
More informationCapturing Skeleton-based Animation Data from a Video
Capturing Skeleton-based Animation Data from a Video Liang-Yu Shih, Bing-Yu Chen National Taiwan University E-mail: xdd@cmlab.csie.ntu.edu.tw, robin@ntu.edu.tw ABSTRACT This paper presents a semi-automatic
More informationInverse KKT Motion Optimization: A Newton Method to Efficiently Extract Task Spaces and Cost Parameters from Demonstrations
Inverse KKT Motion Optimization: A Newton Method to Efficiently Extract Task Spaces and Cost Parameters from Demonstrations Peter Englert Machine Learning and Robotics Lab Universität Stuttgart Germany
More informationSemantic 3D Reconstruction of Heads Supplementary Material
Semantic 3D Reconstruction of Heads Supplementary Material Fabio Maninchedda1, Christian Ha ne2,?, Bastien Jacquet3,?, Amae l Delaunoy?, Marc Pollefeys1,4 1 ETH Zurich 2 UC Berkeley 3 Kitware SAS 4 Microsoft
More informationComputational Design. Stelian Coros
Computational Design Stelian Coros Schedule for presentations February 3 5 10 12 17 19 24 26 March 3 5 10 12 17 19 24 26 30 April 2 7 9 14 16 21 23 28 30 Send me: ASAP: 3 choices for dates + approximate
More informationModeling 3D Human Poses from Uncalibrated Monocular Images
Modeling 3D Human Poses from Uncalibrated Monocular Images Xiaolin K. Wei Texas A&M University xwei@cse.tamu.edu Jinxiang Chai Texas A&M University jchai@cse.tamu.edu Abstract This paper introduces an
More informationCoordinate Free Perspective Projection of Points in the Conformal Model Using Transversions
Coordinate Free Perspective Projection of Points in the Conformal Model Using Transversions Stephen Mann Abstract Goldman presented a method for computing a versor form of the perspective projection of
More informationFEATURE-BASED REGISTRATION OF RANGE IMAGES IN DOMESTIC ENVIRONMENTS
FEATURE-BASED REGISTRATION OF RANGE IMAGES IN DOMESTIC ENVIRONMENTS Michael Wünstel, Thomas Röfer Technologie-Zentrum Informatik (TZI) Universität Bremen Postfach 330 440, D-28334 Bremen {wuenstel, roefer}@informatik.uni-bremen.de
More informationInverse Kinematics II and Motion Capture
Mathematical Foundations of Computer Graphics and Vision Inverse Kinematics II and Motion Capture Luca Ballan Institute of Visual Computing Comparison 0 1 A B 2 C 3 Fake exponential map Real exponential
More informationAnimations. Hakan Bilen University of Edinburgh. Computer Graphics Fall Some slides are courtesy of Steve Marschner and Kavita Bala
Animations Hakan Bilen University of Edinburgh Computer Graphics Fall 2017 Some slides are courtesy of Steve Marschner and Kavita Bala Animation Artistic process What are animators trying to do? What tools
More informationClothed and Naked Human Shapes Estimation from a Single Image
Clothed and Naked Human Shapes Estimation from a Single Image Yu Guo, Xiaowu Chen, Bin Zhou, and Qinping Zhao State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and
More informationDynamic Time Warping for Binocular Hand Tracking and Reconstruction
Dynamic Time Warping for Binocular Hand Tracking and Reconstruction Javier Romero, Danica Kragic Ville Kyrki Antonis Argyros CAS-CVAP-CSC Dept. of Information Technology Institute of Computer Science KTH,
More informationLearning Articulated Skeletons From Motion
Learning Articulated Skeletons From Motion Danny Tarlow University of Toronto, Machine Learning with David Ross and Richard Zemel (and Brendan Frey) August 6, 2007 Point Light Displays It's easy for humans
More informationChaplin, Modern Times, 1936
Chaplin, Modern Times, 1936 [A Bucket of Water and a Glass Matte: Special Effects in Modern Times; bonus feature on The Criterion Collection set] Multi-view geometry problems Structure: Given projections
More informationCSE452 Computer Graphics
CSE452 Computer Graphics Lecture 19: From Morphing To Animation Capturing and Animating Skin Deformation in Human Motion, Park and Hodgins, SIGGRAPH 2006 CSE452 Lecture 19: From Morphing to Animation 1
More informationHistogram of 3D Facets: A Characteristic Descriptor for Hand Gesture Recognition
Histogram of 3D Facets: A Characteristic Descriptor for Hand Gesture Recognition Chenyang Zhang, Xiaodong Yang, and YingLi Tian Department of Electrical Engineering The City College of New York, CUNY {czhang10,
More informationPERFORMANCE CAPTURE FROM SPARSE MULTI-VIEW VIDEO
Stefan Krauß, Juliane Hüttl SE, SoSe 2011, HU-Berlin PERFORMANCE CAPTURE FROM SPARSE MULTI-VIEW VIDEO 1 Uses of Motion/Performance Capture movies games, virtual environments biomechanics, sports science,
More informationCOMPUTER ANIMATION 3 KEYFRAME ANIMATION, RIGGING, SKINNING AND CHARACTER ANIMATION. Rémi Ronfard, Animation, M2R MOSIG
COMPUTER ANIMATION 3 KEYFRAME ANIMATION, RIGGING, SKINNING AND CHARACTER ANIMATION Rémi Ronfard, Animation, M2R MOSIG 2 Outline Principles of animation Keyframe interpolation Rigging, skinning and walking
More informationMotion Capture. Motion Capture in Movies. Motion Capture in Games
Motion Capture Motion Capture in Movies 2 Motion Capture in Games 3 4 Magnetic Capture Systems Tethered Sensitive to metal Low frequency (60Hz) Mechanical Capture Systems Any environment Measures joint
More informationDynamic Geometry Processing
Dynamic Geometry Processing EG 2012 Tutorial Will Chang, Hao Li, Niloy Mitra, Mark Pauly, Michael Wand Tutorial: Dynamic Geometry Processing 1 Articulated Global Registration Introduction and Overview
More informationAutomatic 3D Model Construction for Turn-Table Sequences - a simplification
Automatic 3D Model Construction for Turn-Table Sequences - a simplification Fredrik Larsson larsson@isy.liu.se April, Background This report introduces some simplifications to the method by Fitzgibbon
More informationVNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera By Dushyant Mehta, Srinath Sridhar, Oleksandr Sotnychenko, Helge Rhodin, Mohammad Shafiei, Hans-Peter Seidel, Weipeng Xu, Dan Casas, Christian
More informationMotion Estimation. There are three main types (or applications) of motion estimation:
Members: D91922016 朱威達 R93922010 林聖凱 R93922044 謝俊瑋 Motion Estimation There are three main types (or applications) of motion estimation: Parametric motion (image alignment) The main idea of parametric motion
More informationCVPR 2014 Visual SLAM Tutorial Kintinuous
CVPR 2014 Visual SLAM Tutorial Kintinuous kaess@cmu.edu The Robotics Institute Carnegie Mellon University Recap: KinectFusion [Newcombe et al., ISMAR 2011] RGB-D camera GPU 3D/color model RGB TSDF (volumetric
More informationOnline structured learning for Obstacle avoidance
Adarsh Kowdle Cornell University Zhaoyin Jia Cornell University apk64@cornell.edu zj32@cornell.edu Abstract Obstacle avoidance based on a monocular system has become a very interesting area in robotics
More informationPose estimation using a variety of techniques
Pose estimation using a variety of techniques Keegan Go Stanford University keegango@stanford.edu Abstract Vision is an integral part robotic systems a component that is needed for robots to interact robustly
More informationAnimation Lecture 10 Slide Fall 2003
Animation Lecture 10 Slide 1 6.837 Fall 2003 Conventional Animation Draw each frame of the animation great control tedious Reduce burden with cel animation layer keyframe inbetween cel panoramas (Disney
More informationSTRUCTURAL ICP ALGORITHM FOR POSE ESTIMATION BASED ON LOCAL FEATURES
STRUCTURAL ICP ALGORITHM FOR POSE ESTIMATION BASED ON LOCAL FEATURES Marco A. Chavarria, Gerald Sommer Cognitive Systems Group. Christian-Albrechts-University of Kiel, D-2498 Kiel, Germany {mc,gs}@ks.informatik.uni-kiel.de
More informationWhat have we leaned so far?
What have we leaned so far? Camera structure Eye structure Project 1: High Dynamic Range Imaging What have we learned so far? Image Filtering Image Warping Camera Projection Model Project 2: Panoramic
More informationCMSC 425: Lecture 10 Skeletal Animation and Skinning
CMSC 425: Lecture 10 Skeletal Animation and Skinning Reading: Chapt 11 of Gregory, Game Engine Architecture. Recap: Last time we introduced the principal elements of skeletal models and discussed forward
More informationEE795: Computer Vision and Intelligent Systems
EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 WRI C225 Lecture 02 130124 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Basics Image Formation Image Processing 3 Intelligent
More information3D Computer Vision. Dense 3D Reconstruction II. Prof. Didier Stricker. Christiano Gava
3D Computer Vision Dense 3D Reconstruction II Prof. Didier Stricker Christiano Gava Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de
More informationICPIK: Inverse Kinematics based Articulated-ICP
ICPIK: Inverse Kinematics based Articulated-ICP Shachar Fleishman Mark Kliger Alon Lerner Gershom Kutliroff Intel {shahar.fleishman,mark.kliger,alan.lerner,gershom.kutliroff}@intel.com Abstract In this
More informationUsing temporal seeding to constrain the disparity search range in stereo matching
Using temporal seeding to constrain the disparity search range in stereo matching Thulani Ndhlovu Mobile Intelligent Autonomous Systems CSIR South Africa Email: tndhlovu@csir.co.za Fred Nicolls Department
More informationMultiple camera fusion based on DSmT for tracking objects on ground plane
Multiple camera fusion based on DSmT for tracking objects on ground plane Esteban Garcia and Leopoldo Altamirano National Institute for Astrophysics, Optics and Electronics Puebla, Mexico eomargr@inaoep.mx,
More informationThis week. CENG 732 Computer Animation. Warping an Object. Warping an Object. 2D Grid Deformation. Warping an Object.
CENG 732 Computer Animation Spring 2006-2007 Week 4 Shape Deformation Animating Articulated Structures: Forward Kinematics/Inverse Kinematics This week Shape Deformation FFD: Free Form Deformation Hierarchical
More informationSurfNet: Generating 3D shape surfaces using deep residual networks-supplementary Material
SurfNet: Generating 3D shape surfaces using deep residual networks-supplementary Material Ayan Sinha MIT Asim Unmesh IIT Kanpur Qixing Huang UT Austin Karthik Ramani Purdue sinhayan@mit.edu a.unmesh@gmail.com
More informationT6: Position-Based Simulation Methods in Computer Graphics. Jan Bender Miles Macklin Matthias Müller
T6: Position-Based Simulation Methods in Computer Graphics Jan Bender Miles Macklin Matthias Müller Jan Bender Organizer Professor at the Visual Computing Institute at Aachen University Research topics
More informationShape Preserving RGB-D Depth Map Restoration
Shape Preserving RGB-D Depth Map Restoration Wei Liu 1, Haoyang Xue 1, Yun Gu 1, Qiang Wu 2, Jie Yang 1, and Nikola Kasabov 3 1 The Key Laboratory of Ministry of Education for System Control and Information
More information3D Computer Vision. Depth Cameras. Prof. Didier Stricker. Oliver Wasenmüller
3D Computer Vision Depth Cameras Prof. Didier Stricker Oliver Wasenmüller Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de
More information