CS468: 3D Deep Learning on Point Cloud Data. class label part label. Hao Su. image. May 10, 2017
|
|
- Marvin Weaver
- 5 years ago
- Views:
Transcription
1 CS468: 3D Deep Learning on Point Cloud Data class label part label Hao Su image. May 10, 2017
2 Agenda Point cloud generation Point cloud analysis
3 CVPR 17, Point Set Generation Pipeline render
4 CVPR 17, Point Set Generation Pipeline 2K object categories 200K shapes ~10M image/point set pairs render sample Groundtruth point set
5 CVPR 17, Point Set Generation Pipeline Prediction Shape predictor (f) render sample Groundtruth point set
6 CVPR 17, Point Set Generation Pipeline Prediction Shape predictor (f) render A set is invariant up to permutation sample Groundtruth point set
7 CVPR 17, Point Set Generation Pipeline Prediction render Shape predictor (f) Loss on sets (L) sample Groundtruth point set
8 CVPR 17, Point Set Generation Pipeline Prediction render Shape predictor (f) Loss on sets (L) sample Groundtruth point set
9 CVPR 17, Point Set Generation Set comparison Given two sets of points, measure their discrepancy
10 CVPR 17, Point Set Generation Set comparison Given two sets of points, measure their discrepancy Key challenge: correspondence problem
11 CVPR 17, Point Set Generation Correspondence (I): optimal assignment Given two sets of points, measure their discrepancy a.k.a Earth Mover s distance (EMD)
12 CVPR 17, Point Set Generation Correspondence (II): closest point Given two sets of points, measure their discrepancy a.k.a Chamfer distance (CD)
13 CVPR 17, Point Set Generation Required properties of distance metrics Geometric requirement Computational requirement
14 CVPR 17, Point Set Generation Required properties of distance metrics Geometric requirement Reflects natural shape differences Induce a nice space for shape interpolations Computational requirement
15 CVPR 17, Point Set Generation How distance metric affects learning? A fundamental issue: inherent ambiguity in 2D-3D dimension lifting
16 CVPR 17, Point Set Generation How distance metric affects learning? A fundamental issue: inherent ambiguity in 2D-3D dimension lifting
17 CVPR 17, Point Set Generation How distance metric affects learning? A fundamental issue: inherent ambiguity in 2D-3D dimension lifting
18 CVPR 17, Point Set Generation How distance metric affects learning? A fundamental issue: inherent ambiguity in 2D-3D dimension lifting By loss minimization, the network tends to predict a mean shape that averages out uncertainty
19 Distance metrics affect mean shapes The mean shape carries characteristics of the distance metric continuous hidden variable (radius) Input EMD mean Chamfer mean CVPR 17, Point Set Generation
20 Mean shapes from distance metrics The mean shape carries characteristics of the distance metric continuous hidden variable (radius) discrete hidden variable (add-on location) Input EMD mean Chamfer mean CVPR 17, Point Set Generation
21 CVPR 17, Point Set Generation Comparison of predictions by EMD versus CD Input EMD Chamfer
22 CVPR 17, Point Set Generation Required properties of distance metrics Geometric requirement Reflects natural shape differences Induce a nice space for shape interpolations Computational requirement Defines a loss function that is numerically easy to optimize
23 CVPR 17, Point Set Generation Computational requirement of metrics To be used as a loss function, the metric has to be Differentiable with respect to point locations Efficient to compute
24 CVPR 17, Point Set Generation Computational requirement of metrics Differentiable with respect to point location Chamfer distance Earth Mover s distance - Simple function of coordinates - In general positions, the correspondence is unique - With infinitesimal movement, the correspondence does not change Conclusion: differentiable almost everywhere
25 CVPR 17, Point Set Generation Computational requirement of metrics Efficient to compute Chamfer distance: trivially parallelizable on CUDA Earth Mover s distance (optimal assignment): - We implement a distributed approximation algorithm on CUDA - Based upon [Bertsekas, 1985], -approximation
26 CVPR 17, Point Set Generation Pipeline Deep network (f) Prediction Loss on sets (L) sample
27 CVPR 17, Point Set Generation Pipeline Encoder shape embedding (f) Predictor Loss on sets (L) sample
28 CVPR 17, Point Set Generation Pipeline Encoder shape embedding (f) Predictor Loss on sets (L) sample
29 CVPR 17, Point Set Generation Pipeline conv... Predictor Loss on sets (L) sample
30 CVPR 17, Point Set Generation Pipeline conv... Predictor Loss on sets (L) sample
31 Natural statistics of geometry Many local structures are common e.g., planar patches, cylindrical patches strong local correlation among point coordinates CVPR 17, Point Set Generation
32 Natural statistics of geometry Many local structures are common e.g., planar patches, cylindrical patches strong local correlation among point coordinates Also some intricate structures points have high local variation CVPR 17, Point Set Generation
33 CVPR 17, Point Set Generation Pipeline Capture common structures conv... Capture intricate structures Deconv branch FC branch Loss on sets (L) sample
34 CVPR 17, Point Set Generation Pipeline Capture common structures conv... Capture intricate structures Deconv branch FC branch Loss on sets (L) sample
35 Review: deconv network n Output D arrays, e.g., 2D segmentation map Common local patterns are learned from data Predict locally correlated data well Weight sharing reduces the number of params Deconv network for image segmentation Credit: FCNN, Long et al.
36 Review: deconv network n Output D arrays, e.g., 2D segmentation map Common local patterns are learned from data Predict locally correlated data well Weight sharing reduces the number of params How to predict curved surfaces in 3D? Deconv network for image segmentation Credit: FCNN, Long et al.
37 Prediction of curved 2D surfaces in 3D Surface parametrization (2D 3D mapping) Credit: Discrete Differential Geometry, Crane et al.
38 Prediction of curved 2D surfaces in 3D Surface parametrization (2D 3D mapping) Credit: Discrete Differential Geometry, Crane et al.
39 Prediction of curved 2D surfaces in 3D Surface parametrization (2D 3D mapping) x-map y-map z-map coordinate maps Credit: Discrete Differential Geometry, Crane et al.
40 CVPR 17, Point Set Generation Parametrization prediction by deconv network Capture common structures conv... Capture intricate structures Deconv branch FC branch Loss on sets (L) sample
41 CVPR 17, Point Set Generation Parametrization prediction by deconv network Capture common structures deconv conv Capture intricate structures FC branch coordinate maps Loss on sets (L) sample
42 CVPR 17, Point Set Generation Parametrization prediction by deconv network Capture common structures deconv conv coordinate maps Note that FC branch Capture The parametrization intricate structures(2d/3d mapping) is learned from data i.e., obtains a network and data friendly parametrization Loss on sets (L) sample
43 Visualization of the learned parameterization Observation: Learns a smooth parametrization Because deconv net tends to predict data with local correlation (xk, yk, zk ) map of x coord map of y coord map of z coord
44 Visualization of the learned parameterization Observation: Learns a smooth parametrization Because deconv net tends to predict data with local correlation Corresponds to smooth surfaces! (xk, yk, zk ) map of x coord map of y coord map of z coord
45
46 Natural statistics of geometry Many local structures are common e.g., planar patches, cylindrical patches strong local correlation among point coordinates Also some intricate structures points have high local variation CVPR 17, Point Set Generation
47 CVPR 17, Point Set Generation Pipeline Capture common structures deconv conv Capture intricate structures FC branch Loss on sets (L) sample
48 CVPR 17, Point Set Generation Pipeline Capture common structures deconv conv dense Capture intricate structures dense fc Loss on sets (L) sample
49 CVPR 17, Point Set Generation Pipeline Capture common structures deconv conv dense Capture intricate structures sample dense fc Points are predicted independently Dense connection introduces more parameters to accommodate high variance Loss on sets (L)
50 Visualization of the effect of FC branch Observation: The arrangement of predicted points are uncorrelated x-coord y-coord z-coord red CVPR 17, Point Set Generation
51 Visualization of the effect of FC branch Observation: The arrangement of predicted points are uncorrelated Located at fine structures x-coord y-coord z-coord red CVPR 17, Point Set Generation
52 Q: Which color corresponds to the deconv branch? FC branch? CVPR 17, Point Set Generation
53 CVPR 17, Point Set Generation Q: Which color corresponds to the deconv branch? FC branch? blue: deconv branch large, smooth structures red: FC branch intricate structures
54 CVPR 17, Point Set Generation Comparison to state-of-the-art Input Ours Ours (post-processed) Groundtruth state-of-the-art (3D-R2N2) Better global structure Better details
55 CVPR 17, Point Set Generation Comparison to state-of-the-art Trained/tested on 2K object categories 1.8 Chamfer Distance (Error) Baseline (mean shape) [Choy et. al, ECCV16] Ours
56 Extension: shape completion for RGBD data RGBD map (input) 90 view of input output: completed point cloud CVPR 17, Point Set Generation
57 How about learning to predict geometric forms? Candidates: Rasterized form (regular grids) Geometric form (irregular) multi-view images depth map volumetric polygonal mesh point cloud primitive-based CAD models
58 Primitive-based assembly We learn to predict a corresponding shape composed by primitives. It allows us to predict consistent compositions across objects.
59 Unsupervised parsing Each point is colored according to the assigned primitive
60 A historical overview Generalized Cylinders, Binford (1971)
61 Approach Encoder Predictor for primitive parameters We predict primitive parameters: size, rotation, translation of M cuboids.
62 Approach We predict primitive parameters: size, rotation, translation of M cuboids. Variable number of parts? We predict primitive existence probability
63 Loss function Loss
64 Loss function construction Basic idea: Chamfer distance!
65 Loss function construction Sample points on the groundtruth mesh and predicted assembly Each point is a linear function of mesh/primitive vertex coordinates Differentiable!
66 Loss function construction Sample points on the groundtruth mesh and predicted assembly Each point is a linear function of mesh/primitive vertex coordinates Differentiable! Speed up the computation leveraging parameterization of primitives
67 Consistent primitive configurations Primitive locations are consistent due to the smoothness of primitive prediction network
68 Unsupervised parsing Mean accuracy (face area) on Shape COSEG chairs.
69 Analysis Shapes become more parsimonious as training progresses (due to our parsimony reward)
70 Image-based modeling
71 Agenda Point cloud generation Point cloud analysis
72 Applications of Point Set Learning Robot Perception What and where are the objects in a LiDAR scanned scene?
73 Applications of Point Set Learning Molecular Biology Can we infer an enzyme s category (reactions they catalyze) from its structure? EcoRV restriction enzyme molecule, LAGUNA DESIGN/SCIENCE PHOTO LIBRARY
74 Directly process point cloud data End-to-end learning for unstructured, unordered point data PointNet Motivation ShapeNet PointNet 74
75 Directly process point cloud data End-to-end learning for unstructured, unordered point data Unified framework for various tasks Object Classification PointNet Part Segmentation Scene Parsing... Motivation ShapeNet PointNet 75
76 Properties of a desired neural network on point clouds Point cloud: N orderless points, each represented by a D dim coordinate D N 2D array representation Motivation ShapeNet PointNet 76
77 Properties of a desired neural network on point clouds Point cloud: N orderless points, each represented by a D dim coordinate D N Permutation invariance 2D array representation Transformation invariance Motivation ShapeNet PointNet 77
78 Properties of a desired neural network on point clouds Point cloud: N orderless points, each represented by a D dim coordinate D D N represents the same set as N 2D array representation Permutation invariance Motivation ShapeNet PointNet 78
79 Permutation invariance: Symmetric function f (x 1, x 2,, x n ) f (x π1, x π 2,, x π n ), x i! D Examples: f (x 1, x 2,, x n ) = max{x 1, x 2,, x n } f (x 1, x 2,, x n ) = x 1 + x x n Motivation ShapeNet PointNet 79
80 Construct symmetric function family Observe: f (x 1, x 2,, x n ) = γ! g(h(x 1 ),,h(x n )) is symmetric if g is symmetric Motivation ShapeNet PointNet 80
81 Construct symmetric function family Observe: f (x 1, x 2,, x n ) = γ! g(h(x 1 ),,h(x n )) is symmetric if g is symmetric h (1,2,3) (1,1,1) (2,3,2) (2,3,4) Motivation ShapeNet PointNet 81
82 Construct symmetric function family Observe: f (x 1, x 2,, x n ) = γ! g(h(x 1 ),,h(x n )) is symmetric if g is symmetric h (1,2,3) (1,1,1) g simple symmetric function (2,3,2) (2,3,4) Motivation ShapeNet PointNet 82
83 Construct symmetric function family Observe: f (x 1, x 2,, x n ) = γ! g(h(x 1 ),,h(x n )) is symmetric if g is symmetric h (1,2,3) (1,1,1) g simple symmetric function γ (2,3,2) (2,3,4) PointNet (vanilla) Motivation ShapeNet PointNet 83
84 Q: What symmetric functions can be constructed by PointNet? Symmetric functions PointNet (vanilla) Motivation ShapeNet PointNet 84
85 A: Universal approximation to continuous symmetric functions Theorem: A Hausdorff continuous symmetric function approximated by PointNet. f :2 X! can be arbitrarily S! d, PointNet (vanilla) Motivation ShapeNet PointNet 85
86 PointNet Architecture
87 Results on Object Classification Object Classification Accuracy on ModelNet40
88 Results on Object Part Segmentation
89 Results on Object Part Segmentation Part Segmentation miou on ShapeNet Part Dataset
90 Results on Semantic Scene Segmentation
91 Results on Semantic Scene Parsing Semantic Segmentation (point based) on Stanford Semantic Parsing dataset 3D Object Detection (bounding box based)
92 Robustness to Data Corruption
93 Robustness to Data Corruption
94 Visualizing Point Functions Compact View: 1x3 FCs 1x1024 Expanded View: 1x3 FC FC FC FC FC x1024 Which input point will activate neuron j? Find the top-k points in a dense volumetric grid that activates neuron j.
95 Visualizing Point Functions
96 Visualizing Global Point Cloud Features What s captured and left out here?
97 Visualizing Global Point Cloud Features
98 Visualizing Global Point Cloud Features (OOS)
99 Previous Work: PointNet v1.0 Segmentation Network Point Embeddings
100 Previous Work: PointNet v1.0 Segmentation Network Tiled Global Features Point Embeddings
101 Previous Work: PointNet v1.0 Segmentation Network Tiled Global Features Point Embeddings No local context for each point!
102 Limitations of PointNet v1.0 Hierarchical Feature Learning Increasing receptive field 3D CNN (Wu et al.)
103 Limitations of PointNet v1.0 Hierarchical Feature Learning Increasing receptive field Global Feature Learning Receptive field: one point OR all points v.s. 3D CNN (Wu et al.) PointNet (vanilla) (Qi et al.)
104 Limitations of PointNet v1.0 Artifacts in segmentation tasks: Semantic segmentation in randomly translated table-cup scene. Instance segmentation in tablechair-cup scene
105 Limitations of PointNet v1.0 Artifacts in segmentation tasks: Semantic segmentation in randomly translated table-cup scene. Global feature depends on absolute XYZ! Instance segmentation in tablechair-cup scene Hard to generalize to unseen point configurations
106 Question How to learn local context feature for points? Use PointNet in local regions, aggregate local region features by PointNet again.. Hierarchical feature learning!
107 Multi-Scale PointNet for Hierarchical Feature Learning Charles Ruizhongtai Qi Multi-Scale PointNet for Hierarchical Feature Learning in Point Sets 107
108 PointNet v2.0: Multi-Scale PointNet N points in (x,y)
109 PointNet v2.0: Multi-Scale PointNet Local Coordinates! N points in (x,y) k local points in (x,y )
110 PointNet v2.0: Multi-Scale PointNet PointNet v1.0 N points in (x,y) k local points in (x,y ) feature vector (mark as ) for local point cloud
111 PointNet v2.0: Multi-Scale PointNet PointNet Module/Layer: Farthest Point Sampling + Grouping + PointNet v1.0 N points in (x,y) N1 points in (x,y,f)
112 PointNet v2.0: Multi-Scale PointNet N points in (x,y) N1 points in (x,y,f) N2 points in (x,y,f )
113 PointNet v2.0: Multi-Scale PointNet N points in (x,y) N1 points in (x,y,f) N2 points in (x,y,f )
114 PointNet v2.0: Multi-Scale PointNet N points in (x,y) N1 points in (x,y,f) N2 points in (x,y,f ) 1. Larger receptive field in higher layers 2. Less points in higher layers (more scalable) 3. Weight sharing 4. Translation invariance (local coordinates in local regions)
115 Discussions on Multi-Scale PointNet Charles Ruizhongtai Qi Multi-Scale PointNet for Hierarchical Feature Learning in Point Sets 115
116 Multi-Scale PointNet v.s. PointNet v1.0 Three-layer Multi-Scale PointNet: N points in (x,y) N1 points in (x,y,f) N2 points in (x,y,f ) One-layer Multi-Scale PointNet <=> PointNet v1.0 N points in (x,y)
117 PointNet Layer v.s. Convolution Layer PointNet Layer Convolution Layer PointNet v1.0 Input: Operation: Neighbor -hood: Point set MLP + max pooling Distance query Dense array Multiply and add Array index
118 Multi-Scale PointNet v.s. Graph CNN Unexpectedly strong relation with Graph CNN: Joan Bruna et al. Spectral Networks and Deep Locally Connected Networks on Graphs. ICLR 2014
119 Multi-Scale PointNet v.s. Graph CNN Local feature extraction, graph coarsening, repeat.. Joan Bruna et al. Spectral Networks and Deep Locally Connected Networks on Graphs. ICLR 2014
120 Multi-Scale PointNet v.s. Graph CNN In Graph CNN s perspective: Multi-Scale PointNet defines 1. Graph connectivity through Euclidean distance 2. Graph coarsening by farthest point sampling 3. Local feature extraction with PointNet (v1.0) Multi-scale PointNet Graph CNN
121 Relations to OctNet (Octree based 3D CNN) OctNet in Graph CNN s perspective: 1. Both connectivity and graph coarsening are defined by the Octree. 2. Local feature extraction by convolution layer. OctNet: Learning Deep 3D Representations at High Resolutions Gernot Riegler, Ali Osman Ulusoy and Andreas Geiger
122 Relations to OctNet (Octree based 3D CNN) OctNet in Graph CNN s perspective: In Multi-Scale PointNet 1. Both connectivity and graph coarsening are defined by the Octree. 2. Local feature extraction by convolution layer. By ground distance By PointNet (v1.0) OctNet: Learning Deep 3D Representations at High Resolutions Gernot Riegler, Ali Osman Ulusoy and Andreas Geiger
Seeing the unseen. Data-driven 3D Understanding from Single Images. Hao Su
Seeing the unseen Data-driven 3D Understanding from Single Images Hao Su Image world Shape world 3D perception from a single image Monocular vision a typical prey a typical predator Cited from https://en.wikipedia.org/wiki/binocular_vision
More information3D Deep Learning on Geometric Forms. Hao Su
3D Deep Learning on Geometric Forms Hao Su Many 3D representations are available Candidates: multi-view images depth map volumetric polygonal mesh point cloud primitive-based CAD models 3D representation
More informationPointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. Charles R. Qi* Hao Su* Kaichun Mo Leonidas J. Guibas
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation Charles R. Qi* Hao Su* Kaichun Mo Leonidas J. Guibas Big Data + Deep Representation Learning Robot Perception Augmented Reality
More informationPointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space Sikai Zhong February 14, 2018 COMPUTER SCIENCE Table of contents 1. PointNet 2. PointNet++ 3. Experiments 1 PointNet Property
More information3D Deep Learning
3D Deep Learning Tutorial@CVPR2017 Hao Su (UCSD) Leonidas Guibas (Stanford) Michael Bronstein (Università della Svizzera Italiana) Evangelos Kalogerakis (UMass) Jimei Yang (Adobe Research) Charles Qi (Stanford)
More information3D Shape Segmentation with Projective Convolutional Networks
3D Shape Segmentation with Projective Convolutional Networks Evangelos Kalogerakis 1 Melinos Averkiou 2 Subhransu Maji 1 Siddhartha Chaudhuri 3 1 University of Massachusetts Amherst 2 University of Cyprus
More informationDeep Models for 3D Reconstruction
Deep Models for 3D Reconstruction Andreas Geiger Autonomous Vision Group, MPI for Intelligent Systems, Tübingen Computer Vision and Geometry Group, ETH Zürich October 12, 2017 Max Planck Institute for
More informationarxiv: v1 [cs.cv] 28 Nov 2018
MeshNet: Mesh Neural Network for 3D Shape Representation Yutong Feng, 1 Yifan Feng, 2 Haoxuan You, 1 Xibin Zhao 1, Yue Gao 1 1 BNRist, KLISS, School of Software, Tsinghua University, China. 2 School of
More informationPOINT CLOUD DEEP LEARNING
POINT CLOUD DEEP LEARNING Innfarn Yoo, 3/29/28 / 57 Introduction AGENDA Previous Work Method Result Conclusion 2 / 57 INTRODUCTION 3 / 57 2D OBJECT CLASSIFICATION Deep Learning for 2D Object Classification
More informationECCV Presented by: Boris Ivanovic and Yolanda Wang CS 331B - November 16, 2016
ECCV 2016 Presented by: Boris Ivanovic and Yolanda Wang CS 331B - November 16, 2016 Fundamental Question What is a good vector representation of an object? Something that can be easily predicted from 2D
More informationVolumetric and Multi-View CNNs for Object Classification on 3D Data Supplementary Material
Volumetric and Multi-View CNNs for Object Classification on 3D Data Supplementary Material Charles R. Qi Hao Su Matthias Nießner Angela Dai Mengyuan Yan Leonidas J. Guibas Stanford University 1. Details
More informationLearning from 3D Data
Learning from 3D Data Thomas Funkhouser Princeton University* * On sabbatical at Stanford and Google Disclaimer: I am talking about the work of these people Shuran Song Andy Zeng Fisher Yu Yinda Zhang
More informationPhoto-realistic Renderings for Machines Seong-heum Kim
Photo-realistic Renderings for Machines 20105034 Seong-heum Kim CS580 Student Presentations 2016.04.28 Photo-realistic Renderings for Machines Scene radiances Model descriptions (Light, Shape, Material,
More informationSupplementary A. Overview. C. Time and Space Complexity. B. Shape Retrieval. D. Permutation Invariant SOM. B.1. Dataset
Supplementary A. Overview This supplementary document provides more technical details and experimental results to the main paper. Shape retrieval experiments are demonstrated with ShapeNet Core55 dataset
More information3D Object Classification via Spherical Projections
3D Object Classification via Spherical Projections Zhangjie Cao 1,QixingHuang 2,andRamaniKarthik 3 1 School of Software Tsinghua University, China 2 Department of Computer Science University of Texas at
More informationAn Empirical Study of Generative Adversarial Networks for Computer Vision Tasks
An Empirical Study of Generative Adversarial Networks for Computer Vision Tasks Report for Undergraduate Project - CS396A Vinayak Tantia (Roll No: 14805) Guide: Prof Gaurav Sharma CSE, IIT Kanpur, India
More information3D Shape Analysis with Multi-view Convolutional Networks. Evangelos Kalogerakis
3D Shape Analysis with Multi-view Convolutional Networks Evangelos Kalogerakis 3D model repositories [3D Warehouse - video] 3D geometry acquisition [KinectFusion - video] 3D shapes come in various flavors
More informationObject Localization, Segmentation, Classification, and Pose Estimation in 3D Images using Deep Learning
Allan Zelener Dissertation Proposal December 12 th 2016 Object Localization, Segmentation, Classification, and Pose Estimation in 3D Images using Deep Learning Overview 1. Introduction to 3D Object Identification
More informationDeep Learning on Point Sets for 3D Classification and Segmentation
Deep Learning on Point Sets for 3D Classification and Segmentation Charles Ruizhongtai Qi Stanford University rqi@stanford.edu Abstract Point cloud is an important type of geometric data structure. Due
More informationJOINT DETECTION AND SEGMENTATION WITH DEEP HIERARCHICAL NETWORKS. Zhao Chen Machine Learning Intern, NVIDIA
JOINT DETECTION AND SEGMENTATION WITH DEEP HIERARCHICAL NETWORKS Zhao Chen Machine Learning Intern, NVIDIA ABOUT ME 5th year PhD student in physics @ Stanford by day, deep learning computer vision scientist
More informationPaper Motivation. Fixed geometric structures of CNN models. CNNs are inherently limited to model geometric transformations
Paper Motivation Fixed geometric structures of CNN models CNNs are inherently limited to model geometric transformations Higher-level features combine lower-level features at fixed positions as a weighted
More informationLearning to generate 3D shapes
Learning to generate 3D shapes Subhransu Maji College of Information and Computer Sciences University of Massachusetts, Amherst http://people.cs.umass.edu/smaji August 10, 2018 @ Caltech Creating 3D shapes
More informationL1 - Introduction. Contents. Introduction of CAD/CAM system Components of CAD/CAM systems Basic concepts of graphics programming
L1 - Introduction Contents Introduction of CAD/CAM system Components of CAD/CAM systems Basic concepts of graphics programming 1 Definitions Computer-Aided Design (CAD) The technology concerned with the
More information08 An Introduction to Dense Continuous Robotic Mapping
NAVARCH/EECS 568, ROB 530 - Winter 2018 08 An Introduction to Dense Continuous Robotic Mapping Maani Ghaffari March 14, 2018 Previously: Occupancy Grid Maps Pose SLAM graph and its associated dense occupancy
More informationUsing Faster-RCNN to Improve Shape Detection in LIDAR
Using Faster-RCNN to Improve Shape Detection in LIDAR TJ Melanson Stanford University Stanford, CA 94305 melanson@stanford.edu Abstract In this paper, I propose a method for extracting objects from unordered
More informationDeep Learning for Robust Normal Estimation in Unstructured Point Clouds. Alexandre Boulch. Renaud Marlet
Deep Learning for Robust Normal Estimation in Unstructured Point Clouds Alexandre Boulch Renaud Marlet Normal estimation in point clouds Normal: 3D normalized vector At each point: local orientation of
More informationLSTM and its variants for visual recognition. Xiaodan Liang Sun Yat-sen University
LSTM and its variants for visual recognition Xiaodan Liang xdliang328@gmail.com Sun Yat-sen University Outline Context Modelling with CNN LSTM and its Variants LSTM Architecture Variants Application in
More informationMULTI-LEVEL 3D CONVOLUTIONAL NEURAL NETWORK FOR OBJECT RECOGNITION SAMBIT GHADAI XIAN LEE ADITYA BALU SOUMIK SARKAR ADARSH KRISHNAMURTHY
MULTI-LEVEL 3D CONVOLUTIONAL NEURAL NETWORK FOR OBJECT RECOGNITION SAMBIT GHADAI XIAN LEE ADITYA BALU SOUMIK SARKAR ADARSH KRISHNAMURTHY Outline Object Recognition Multi-Level Volumetric Representations
More information3D model classification using convolutional neural network
3D model classification using convolutional neural network JunYoung Gwak Stanford jgwak@cs.stanford.edu Abstract Our goal is to classify 3D models directly using convolutional neural network. Most of existing
More informationDeep Incremental Scene Understanding. Federico Tombari & Christian Rupprecht Technical University of Munich, Germany
Deep Incremental Scene Understanding Federico Tombari & Christian Rupprecht Technical University of Munich, Germany C. Couprie et al. "Toward Real-time Indoor Semantic Segmentation Using Depth Information"
More information9. Three Dimensional Object Representations
9. Three Dimensional Object Representations Methods: Polygon and Quadric surfaces: For simple Euclidean objects Spline surfaces and construction: For curved surfaces Procedural methods: Eg. Fractals, Particle
More informationAI Ukraine Point cloud labeling using machine learning
AI Ukraine - 2017 Point cloud labeling using machine learning Andrii Babii apratster@gmail.com Data sources 1. LIDAR 2. 3D IR cameras 3. Generated from 2D sources 3D dataset: http://kos.informatik.uni-osnabrueck.de/3dscans/
More informationPoint2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network
Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network Xinhai Liu, Zhizhong Han,2, Yu-Shen Liu, Matthias Zwicker 2 School of Software,
More informationDeepIM: Deep Iterative Matching for 6D Pose Estimation - Supplementary Material
DeepIM: Deep Iterative Matching for 6D Pose Estimation - Supplementary Material Yi Li 1, Gu Wang 1, Xiangyang Ji 1, Yu Xiang 2, and Dieter Fox 2 1 Tsinghua University, BNRist 2 University of Washington
More informationVisual Computing TUM
Visual Computing Group @ TUM Visual Computing Group @ TUM BundleFusion Real-time 3D Reconstruction Scalable scene representation Global alignment and re-localization TOG 17 [Dai et al.]: BundleFusion Real-time
More informationLecture 10 CNNs on Graphs
Lecture 10 CNNs on Graphs CMSC 35246: Deep Learning Shubhendu Trivedi & Risi Kondor University of Chicago April 26, 2017 Two Scenarios For CNNs on graphs, we have two distinct scenarios: Scenario 1: Each
More informationData Representation in Visualisation
Data Representation in Visualisation Visualisation Lecture 4 Taku Komura Institute for Perception, Action & Behaviour School of Informatics Taku Komura Data Representation 1 Data Representation We have
More information3D Attention-Driven Depth Acquisition for Object Identification
3D Attention-Driven Depth Acquisition for Object Identification Kai Xu, Yifei Shi, Lintao Zheng, Junyu Zhang, Min Liu, Hui Huang, Hao Su, Daniel Cohen-Or and Baoquan Chen National University of Defense
More informationOctree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs Supplementary Material
Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs Supplementary Material Peak memory usage, GB 10 1 0.1 0.01 OGN Quadratic Dense Cubic Iteration time, s 10
More informationCOMP 551 Applied Machine Learning Lecture 16: Deep Learning
COMP 551 Applied Machine Learning Lecture 16: Deep Learning Instructor: Ryan Lowe (ryan.lowe@cs.mcgill.ca) Slides mostly by: Class web page: www.cs.mcgill.ca/~hvanho2/comp551 Unless otherwise noted, all
More information3D Convolutional Neural Networks for Landing Zone Detection from LiDAR
3D Convolutional Neural Networks for Landing Zone Detection from LiDAR Daniel Mataruna and Sebastian Scherer Presented by: Sabin Kafle Outline Introduction Preliminaries Approach Volumetric Density Mapping
More informationThree-Dimensional Object Detection and Layout Prediction using Clouds of Oriented Gradients
ThreeDimensional Object Detection and Layout Prediction using Clouds of Oriented Gradients Authors: Zhile Ren, Erik B. Sudderth Presented by: Shannon Kao, Max Wang October 19, 2016 Introduction Given an
More information3D Modeling techniques
3D Modeling techniques 0. Reconstruction From real data (not covered) 1. Procedural modeling Automatic modeling of a self-similar objects or scenes 2. Interactive modeling Provide tools to computer artists
More informationCross-domain Deep Encoding for 3D Voxels and 2D Images
Cross-domain Deep Encoding for 3D Voxels and 2D Images Jingwei Ji Stanford University jingweij@stanford.edu Danyang Wang Stanford University danyangw@stanford.edu 1. Introduction 3D reconstruction is one
More informationLecture 7: Semantic Segmentation
Semantic Segmentation CSED703R: Deep Learning for Visual Recognition (207F) Segmenting images based on its semantic notion Lecture 7: Semantic Segmentation Bohyung Han Computer Vision Lab. bhhanpostech.ac.kr
More informationFrom 3D descriptors to monocular 6D pose: what have we learned?
ECCV Workshop on Recovering 6D Object Pose From 3D descriptors to monocular 6D pose: what have we learned? Federico Tombari CAMP - TUM Dynamic occlusion Low latency High accuracy, low jitter No expensive
More informationMatching and Recognition in 3D. Based on slides by Tom Funkhouser and Misha Kazhdan
Matching and Recognition in 3D Based on slides by Tom Funkhouser and Misha Kazhdan From 2D to 3D: Some Things Easier No occlusion (but sometimes missing data instead) Segmenting objects often simpler From
More informationSemantic Segmentation
Semantic Segmentation UCLA:https://goo.gl/images/I0VTi2 OUTLINE Semantic Segmentation Why? Paper to talk about: Fully Convolutional Networks for Semantic Segmentation. J. Long, E. Shelhamer, and T. Darrell,
More informationSupplementary Material for Ensemble Diffusion for Retrieval
Supplementary Material for Ensemble Diffusion for Retrieval Song Bai 1, Zhichao Zhou 1, Jingdong Wang, Xiang Bai 1, Longin Jan Latecki 3, Qi Tian 4 1 Huazhong University of Science and Technology, Microsoft
More informationFrom processing to learning on graphs
From processing to learning on graphs Patrick Pérez Maths and Images in Paris IHP, 2 March 2017 Signals on graphs Natural graph: mesh, network, etc., related to a real structure, various signals can live
More informationCSE528 Computer Graphics: Theory, Algorithms, and Applications
CSE528 Computer Graphics: Theory, Algorithms, and Applications Hong Qin State University of New York at Stony Brook (Stony Brook University) Stony Brook, New York 11794--4400 Tel: (631)632-8450; Fax: (631)632-8334
More information3D Object Recognition and Scene Understanding from RGB-D Videos. Yu Xiang Postdoctoral Researcher University of Washington
3D Object Recognition and Scene Understanding from RGB-D Videos Yu Xiang Postdoctoral Researcher University of Washington 1 2 Act in the 3D World Sensing & Understanding Acting Intelligent System 3D World
More informationPresented at the FIG Congress 2018, May 6-11, 2018 in Istanbul, Turkey
Presented at the FIG Congress 2018, May 6-11, 2018 in Istanbul, Turkey Evangelos MALTEZOS, Charalabos IOANNIDIS, Anastasios DOULAMIS and Nikolaos DOULAMIS Laboratory of Photogrammetry, School of Rural
More informationPerceiving the 3D World from Images and Videos. Yu Xiang Postdoctoral Researcher University of Washington
Perceiving the 3D World from Images and Videos Yu Xiang Postdoctoral Researcher University of Washington 1 2 Act in the 3D World Sensing & Understanding Acting Intelligent System 3D World 3 Understand
More informationarxiv: v1 [cs.cv] 13 Feb 2018
Recurrent Slice Networks for 3D Segmentation on Point Clouds Qiangui Huang Weiyue Wang Ulrich Neumann University of Southern California Los Angeles, California {qianguih,weiyuewa,uneumann}@uscedu arxiv:180204402v1
More informationSu et al. Shape Descriptors - III
Su et al. Shape Descriptors - III Siddhartha Chaudhuri http://www.cse.iitb.ac.in/~cs749 Funkhouser; Feng, Liu, Gong Recap Global A shape descriptor is a set of numbers that describes a shape in a way that
More informationInput. Output. Problem Definition. Rectified stereo image pair All correspondences lie in same scan lines
Problem Definition 3 Input Rectified stereo image pair All correspondences lie in same scan lines Output Disparity map of the reference view Foreground: large disparity Background: small disparity Matching
More informationSubdivision Surfaces. Course Syllabus. Course Syllabus. Modeling. Equivalence of Representations. 3D Object Representations
Subdivision Surfaces Adam Finkelstein Princeton University COS 426, Spring 2003 Course Syllabus I. Image processing II. Rendering III. Modeling IV. Animation Image Processing (Rusty Coleman, CS426, Fall99)
More informationDiscrete Optimization of Ray Potentials for Semantic 3D Reconstruction
Discrete Optimization of Ray Potentials for Semantic 3D Reconstruction Marc Pollefeys Joined work with Nikolay Savinov, Christian Haene, Lubor Ladicky 2 Comparison to Volumetric Fusion Higher-order ray
More informationCorrespondence. CS 468 Geometry Processing Algorithms. Maks Ovsjanikov
Shape Matching & Correspondence CS 468 Geometry Processing Algorithms Maks Ovsjanikov Wednesday, October 27 th 2010 Overall Goal Given two shapes, find correspondences between them. Overall Goal Given
More informationDeep Learning on Graphs
Deep Learning on Graphs with Graph Convolutional Networks Hidden layer Hidden layer Input Output ReLU ReLU, 22 March 2017 joint work with Max Welling (University of Amsterdam) BDL Workshop @ NIPS 2016
More informationMulti-view 3D Models from Single Images with a Convolutional Network
Multi-view 3D Models from Single Images with a Convolutional Network Maxim Tatarchenko University of Freiburg Skoltech - 2nd Christmas Colloquium on Computer Vision Humans have prior knowledge about 3D
More informationMay I Have Your Attention Please? (said one neuron to another)
May I Have Your Attention Please? (said one neuron to another) Ani Kembhavi Allen Institute for Artificial Intelligence The world of visual illustrations and many more Science Diagrams Maps 3d visualizations
More informationDeep Learning on Graphs
Deep Learning on Graphs with Graph Convolutional Networks Hidden layer Hidden layer Input Output ReLU ReLU, 6 April 2017 joint work with Max Welling (University of Amsterdam) The success story of deep
More informationLEARNING TO GENERATE CHAIRS WITH CONVOLUTIONAL NEURAL NETWORKS
LEARNING TO GENERATE CHAIRS WITH CONVOLUTIONAL NEURAL NETWORKS Alexey Dosovitskiy, Jost Tobias Springenberg and Thomas Brox University of Freiburg Presented by: Shreyansh Daftry Visual Learning and Recognition
More information3D Modeling: Surfaces
CS 430/536 Computer Graphics I 3D Modeling: Surfaces Week 8, Lecture 16 David Breen, William Regli and Maxim Peysakhov Geometric and Intelligent Computing Laboratory Department of Computer Science Drexel
More informationIs 2D Information Enough For Viewpoint Estimation? Amir Ghodrati, Marco Pedersoli, Tinne Tuytelaars BMVC 2014
Is 2D Information Enough For Viewpoint Estimation? Amir Ghodrati, Marco Pedersoli, Tinne Tuytelaars BMVC 2014 Problem Definition Viewpoint estimation: Given an image, predicting viewpoint for object of
More informationFully-Convolutional Siamese Networks for Object Tracking
Fully-Convolutional Siamese Networks for Object Tracking Luca Bertinetto*, Jack Valmadre*, João Henriques, Andrea Vedaldi and Philip Torr www.robots.ox.ac.uk/~luca luca.bertinetto@eng.ox.ac.uk Tracking
More informationCOMPARATIVE DEEP LEARNING FOR CONTENT- BASED MEDICAL IMAGE RETRIEVAL
1 COMPARATIVE DEEP LEARNING FOR CONTENT- BASED MEDICAL IMAGE RETRIEVAL ADITYA SRIRAM DECEMBER 1 st, 2016 Aditya Sriram CS846 Software Engineering for Big Data December 1, 2016 TOPICS 2 Paper Synopsis Content-Based
More informationMulti-View 3D Object Detection Network for Autonomous Driving
Multi-View 3D Object Detection Network for Autonomous Driving Xiaozhi Chen, Huimin Ma, Ji Wan, Bo Li, Tian Xia CVPR 2017 (Spotlight) Presented By: Jason Ku Overview Motivation Dataset Network Architecture
More informationLecture 13 Segmentation and Scene Understanding Chris Choy, Ph.D. candidate Stanford Vision and Learning Lab (SVL)
Lecture 13 Segmentation and Scene Understanding Chris Choy, Ph.D. candidate Stanford Vision and Learning Lab (SVL) http://chrischoy.org Stanford CS231A 1 Understanding a Scene Objects Chairs, Cups, Tables,
More informationCS 395T Numerical Optimization for Graphics and AI (3D Vision) Qixing Huang August 29 th 2018
CS 395T Numerical Optimization for Graphics and AI (3D Vision) Qixing Huang August 29 th 2018 3D Vision Understanding geometric relations between images and the 3D world between images Obtaining 3D information
More informationEncoder-Decoder Networks for Semantic Segmentation. Sachin Mehta
Encoder-Decoder Networks for Semantic Segmentation Sachin Mehta Outline > Overview of Semantic Segmentation > Encoder-Decoder Networks > Results What is Semantic Segmentation? Input: RGB Image Output:
More informationgraphics pipeline computer graphics graphics pipeline 2009 fabio pellacini 1
graphics pipeline computer graphics graphics pipeline 2009 fabio pellacini 1 graphics pipeline sequence of operations to generate an image using object-order processing primitives processed one-at-a-time
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 informationDepth from Stereo. Dominic Cheng February 7, 2018
Depth from Stereo Dominic Cheng February 7, 2018 Agenda 1. Introduction to stereo 2. Efficient Deep Learning for Stereo Matching (W. Luo, A. Schwing, and R. Urtasun. In CVPR 2016.) 3. Cascade Residual
More informationMultiresolution Tree Networks for 3D Point Cloud Processing
Multiresolution Tree Networks for 3D Point Cloud Processing Matheus Gadelha, Rui Wang and Subhransu Maji College of Information and Computer Sciences, University of Massachusetts - Amherst {mgadelha, ruiwang,
More informationLarge-Scale Point Cloud Classification Benchmark
Large-Scale Point Cloud Classification Benchmark www.semantic3d.net IGP & CVG, ETH Zürich www.semantic3d.net, info@semantic3d.net 7/6/2016 1 Timo Hackel Nikolay Savinov Ľubor Ladický Jan Dirk Wegner Konrad
More informationFully-Convolutional Siamese Networks for Object Tracking
Fully-Convolutional Siamese Networks for Object Tracking Luca Bertinetto*, Jack Valmadre*, João Henriques, Andrea Vedaldi and Philip Torr www.robots.ox.ac.uk/~luca luca.bertinetto@eng.ox.ac.uk Tracking
More informationDeep Learning. Architecture Design for. Sargur N. Srihari
Architecture Design for Deep Learning Sargur N. srihari@cedar.buffalo.edu 1 Topics Overview 1. Example: Learning XOR 2. Gradient-Based Learning 3. Hidden Units 4. Architecture Design 5. Backpropagation
More informationParallelizing Graphics Pipeline Execution (+ Basics of Characterizing a Rendering Workload)
Lecture 2: Parallelizing Graphics Pipeline Execution (+ Basics of Characterizing a Rendering Workload) Visual Computing Systems Analyzing a 3D Graphics Workload Where is most of the work done? Memory Vertex
More informationFrom CAD surface models to quality meshes. Patrick LAUG. Projet GAMMA. INRIA Rocquencourt. Outline
From CAD surface models to quality meshes Patrick LAUG Projet GAMMA INRIA Rocquencourt Tetrahedron II Oct. 2007 1 Outline 1. Introduction B-Rep, patches 2. CAD repair ant topology recovery 3. Discretization
More informationSurface Rendering. Surface Rendering
Surface Rendering Surface Rendering Introduce Mapping Methods - Texture Mapping - Environmental Mapping - Bump Mapping Go over strategies for - Forward vs backward mapping 2 1 The Limits of Geometric Modeling
More informationNon-Experts Shape Modeling for Dummies
Non-Experts Shape Modeling for Dummies (Modeling with Interchangeable Parts) Alla Sheffer (joint work with Vladislav Kraevoy & Dan Julius) Motivation - Easy creation of 3D Content Currently 3D modeling
More informationTriangle meshes I. CS 4620 Lecture 2
Triangle meshes I CS 4620 Lecture 2 2014 Steve Marschner 1 spheres Andrzej Barabasz approximate sphere Rineau & Yvinec CGAL manual 2014 Steve Marschner 2 finite element analysis PATRIOT Engineering 2014
More information0. Introduction: What is Computer Graphics? 1. Basics of scan conversion (line drawing) 2. Representing 2D curves
CSC 418/2504: Computer Graphics Course web site (includes course information sheet): http://www.dgp.toronto.edu/~elf Instructor: Eugene Fiume Office: BA 5266 Phone: 416 978 5472 (not a reliable way) Email:
More informationBilinear Models for Fine-Grained Visual Recognition
Bilinear Models for Fine-Grained Visual Recognition Subhransu Maji College of Information and Computer Sciences University of Massachusetts, Amherst Fine-grained visual recognition Example: distinguish
More informationarxiv: v1 [cs.cv] 30 Sep 2018
3D-PSRNet: Part Segmented 3D Point Cloud Reconstruction From a Single Image Priyanka Mandikal, Navaneet K L, and R. Venkatesh Babu arxiv:1810.00461v1 [cs.cv] 30 Sep 2018 Indian Institute of Science, Bangalore,
More informationCAPNet: Continuous Approximation Projection For 3D Point Cloud Reconstruction Using 2D Supervision
CAPNet: Continuous Approximation Projection For 3D Point Cloud Reconstruction Using 2D Supervision Navaneet K L *, Priyanka Mandikal * and R. Venkatesh Babu Video Analytics Lab, IISc, Bangalore, India
More informationSpline Curves. Spline Curves. Prof. Dr. Hans Hagen Algorithmic Geometry WS 2013/2014 1
Spline Curves Prof. Dr. Hans Hagen Algorithmic Geometry WS 2013/2014 1 Problem: In the previous chapter, we have seen that interpolating polynomials, especially those of high degree, tend to produce strong
More informationPATTERN CLASSIFICATION AND SCENE ANALYSIS
PATTERN CLASSIFICATION AND SCENE ANALYSIS RICHARD O. DUDA PETER E. HART Stanford Research Institute, Menlo Park, California A WILEY-INTERSCIENCE PUBLICATION JOHN WILEY & SONS New York Chichester Brisbane
More informationFast marching methods
1 Fast marching methods Lecture 3 Alexander & Michael Bronstein tosca.cs.technion.ac.il/book Numerical geometry of non-rigid shapes Stanford University, Winter 2009 Metric discretization 2 Approach I:
More information3D Rasterization II COS 426
3D Rasterization II COS 426 3D Rendering Pipeline (for direct illumination) 3D Primitives Modeling Transformation Lighting Viewing Transformation Projection Transformation Clipping Viewport Transformation
More informationarxiv: v1 [cs.cv] 15 Aug 2018
Convolutional Neural Networks on 3D Surfaces Using Parallel Frames arxiv:1808.04952v1 [cs.cv] 15 Aug 2018 HAO PAN, Microsoft Research Asia SHILIN LIU, University of Science and Technology of China and
More information6.837 Introduction to Computer Graphics Quiz 2 Thursday November 20, :40-4pm One hand-written sheet of notes allowed
6.837 Introduction to Computer Graphics Quiz 2 Thursday November 20, 2003 2:40-4pm One hand-written sheet of notes allowed Name: 1 2 3 4 5 6 7 / 4 / 15 / 5 / 5 / 12 / 2 / 7 Total / 50 1 Animation [ /4]
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 informationUrban Scene Segmentation, Recognition and Remodeling. Part III. Jinglu Wang 11/24/2016 ACCV 2016 TUTORIAL
Part III Jinglu Wang Urban Scene Segmentation, Recognition and Remodeling 102 Outline Introduction Related work Approaches Conclusion and future work o o - - ) 11/7/16 103 Introduction Motivation Motivation
More informationLevel of Details in Computer Rendering
Level of Details in Computer Rendering Ariel Shamir Overview 1. Photo realism vs. Non photo realism (NPR) 2. Objects representations 3. Level of details Photo Realism Vs. Non Pixar Demonstrations Sketching,
More informationCS 112 The Rendering Pipeline. Slide 1
CS 112 The Rendering Pipeline Slide 1 Rendering Pipeline n Input 3D Object/Scene Representation n Output An image of the input object/scene n Stages (for POLYGON pipeline) n Model view Transformation n
More informationECE 6504: Deep Learning for Perception
ECE 6504: Deep Learning for Perception Topics: (Finish) Backprop Convolutional Neural Nets Dhruv Batra Virginia Tech Administrativia Presentation Assignments https://docs.google.com/spreadsheets/d/ 1m76E4mC0wfRjc4HRBWFdAlXKPIzlEwfw1-u7rBw9TJ8/
More information