Fast Patch-based Style Transfer of Arbitrary Style
|
|
- Colleen Jones
- 6 years ago
- Views:
Transcription
1 Fast Patch-based Style Transfer of Arbitrary Style Tian Qi Chen Department of Computer Science University of British Columbia Mark Schmidt Department of Computer Science University of British Columbia Abstract Artistic style transfer is an image synthesis problem where the content of an image is reproduced with the style of another. Recent works show that a visually appealing style transfer can be achieved by using the hidden activations of a pretrained convolutional neural network. However, existing methods either apply (i) an optimization procedure that works for any style image but is very expensive, or (ii) an efficient feedforward network that only allows a limited number of trained styles. In this work we propose a simpler optimization objective based on locality matching that combines the content structure and style textures in a single layer of the pretrained network. We show that our objective has desirable properties such as a simpler optimization landscape and consistent frame-by-frame performance on video. Furthermore, we use 80,000 natural images and 80,000 paintings to train an inverse network that approximates the result of the optimization. This results in a procedure for artistic style transfer that is efficient but also allows arbitrary content and style images. 1 Introduction Famous artists are typically renowned for a particular artistic style, which takes years to develop. Even once perfected, a single piece of art can take days or even months to create. This motivates us to explore efficient computational strategies for creating artistic images. While there is a large classical literature on texture synthesis methods that create artwork from a blank canvas [6, 16, 18, 26], several recent approaches study the problem of transferring the desired style from one image onto the structural content of another image. This approach is known as artistic style transfer. Artistic style transfer based on convolutional neural network (CNN) has recently shown impressive results [7, 8, 9, 17], and even created a market for mobile applications that can stylize user-provided images on demand. Despite this renewed interest, the actual process of style transfer is based on solving a complex optimization procedure, which can take minutes on today s hardware. This may be too slow for applications where we want to stylize videos, and has motivated recent approaches that train another neural network to efficiently approximate the optimum of the optimization problem [14, 24, 25]. While much faster, these approaches sacrifice the versatility of being able to perform style transfer with arbitrary style image, as the feed-forward networks are trained to mimic a certain style or a small set of styles. In this work we propose a method that has addresses these limitations: a new method for artistic style transfer that is efficient but is not limited to a finite set of styles. We tackle this problem by defining a new optimization objective for style transfer that notably only depends on one layer of the CNN (as opposed to existing methods that use multiple layers). The new objective still leads to a visually appealing style transfer while this simple restriction allows us to use an inverse network" to deterministically invert the activations from that layer to yield the stylized image. 30th Conference on Neural Information Processing Systems (NIPS 2016), Barcelona, Spain.
2 2 Our Optimization Formulation The main component of our style transfer method is a patch-based operation for constructing the target activations in a single layer, given the style and content images. We refer to this procedure as swapping the style of an image, as the content image is replaced patch-by-patch by the style image. We only present this operation at a high level here due to space restrictions, but it is possible to formulate this operation as a convolution followed by a simple argmax and then a transposed convolution. Let C and S denote the RGB representations of the content and style images (respectively), and let Φ( ) be the function represented by a fully convolutional part of the pretrained CNN that maps an image from the RGB space to some intermediate activation space. We extract overlapping activation patches after mapping the content and style images to their activations, Φ(C) and Φ(S). Let {φ i (C)} i Nc and {φ j (S)} j Ns denote the set of extracted activation patches for content and style respectively. The activation patches can be extracted with arbitrary size and overlap, although the style and content activation patches must have the same patch size. We then perform a patch-wise similarity matching between the content activation patches and style activation patches, using normalized cross-correlation. In particular, for each content patch we find the style patch maximizing φ ss φ i (C), φ j (S) i (C, S) := arg max φ j(s), j N s φ i (C) φ j (S). (1) We replace every content activation patch φ i (C) with its best matching style activation patch φ ss i (C, S). The complete activations for the style-swapped image, which we denote by Φss (C, S), are then formed by recombining the patches {φ ss i (C, S)} i N c. We average the activation values between overlapping patches, producing a linear interpolation effect in activation space. Thus, the hidden activations can be viewed as coming from a single original image. The stylized image can be computed by placing a loss function on the activation space with target activations Φ ss (C, S). Similar to prior works on style transfer [9, 17], we use the squared-error loss and define our optimization objective as I stylized (C, S) = arg min Φ(I) Φ ss (C, S) 2 + λl T V (I) (2) I R 3 H W where l T V (I) is a total variance regularization term widely used in image generation methods [1, 14, 21]. Because Φ( ) may contain multiple max-pooling operations that downsample the image, we use this regularization as a natural image prior, obtaining spatially smooth results for the re-upsampled image. Since the function Φ( ) is part of a pretrained CNN and is at least once subdifferentiable, (2) can be minimize using standard subgradient-based optimization methods. 3 Approximating the Optimum With an Inverse Network An alternative approach to using optimization methods is to train an inverse network that approximates the optimum of the loss function (2). In particular, instead of placing a loss on the RGB space and trying to optimize in RGB space, our inverse network is trained using the loss (2) on the activations. In particular, we train a network approximating Φ 1 using the loss function 3.1 Training Method 1 min Φ n 1 n Φ( Φ ( ) 1 (Φ j )) Φ j 2 + λl Φ 1 T V (Φ j ). (3) j=1 The function Φ( ) is non-surjective. That is, not all hidden activations correspond to real images. This causes a problem if we only train on real images. In this case the Φ j obtained by (3) from the real images at test time would be inverting activations that are outside the trained domain (as these activations would be the result of style swapping). To ensure the network can invert style-swapped activations, we simply augment the training set to include these types of activations. More precisely, given a set of content and style images (and their 2
3 Standard Deviation Content Image RGB relu1_1 relu2_1 Style Image relu3_1 relu4_1 relu5_1 Figure 1: The effect of style swapping in different layers of VGG-19 [23], and also in RGB space. Due to the naming convention of VGG-19, relux_1 refers to the first ReLU layer after the (X 1)-th maxpooling layer. The style swap operation uses patches of size 3 3 and stride 1, and then the RGB image is constructed using optimization Standard Deviation of Pixels Gatys et al. Li and Wand Style Swap Content Image Gatys et al. with random init Optimization Iteration (a) Style Image Our method with random init (b) Figure 2: (a) Standard deviation of the RGB pixels over the course of optimization is shown for 40 random initializations. The lines show the mean value and the shaded regions are within one standard deviation of the mean. The vertical dashed lines indicate the end of optimization. (b) Samples using random initializations. corresponding activations), we augment the training set with style-swapped activations based on pairs of images. This augmented set of activations is then used to train the inverse network using a stochastic gradient method applied to (3). 4 Experiments Target Layer. The effects of style swapping in different layers of the VGG-19 network are shown in Figure 1 (where in these figures we re using optimization as described in Section 2). We see that while we can style swap directly in RGB space, the result is nothing more than a recolor. As we choose a target layer that is deeper in the network, textures of the style image are more pronounced. We find that style swapping on the relu3_1 layer provides the most visually pleasing results, while staying structurally consistent with the content. We restrict our method to the relu3_1 layer in the following experiments and in the inverse network training. Qualitative results are shown in Figure 4, where our results are placed side-by-side with images stylized using Gatys et al s method. Consistency. Style swapping concatenates the content and style information into a single target feature vector. The optimization procedure is then much easier compared to other approaches. Figure 2 shows the difference in optimization between our formulation and existing works. Random initializations have almost no effect in the stylized result, indicating that we have far fewer local 3
4 Loss Function Validation Loss Optimization InvNet-NoAug InvNet-Aug Iteration Figure 3: Validation loss of inverse networks on 2000 content images and 6 style images, using patches of size 3 3. Method N. Iters. Time/Iter. (s) Total (s) Gatys et al. [9] Li and Wand [17] Style Swap (Optim) Style Swap (InvNet) Table 1: Mean computation times of style transfer methods that can handle arbitary style images. Times are taken for images of resolution on a GeForce GTX 980 Ti. Note that the number of iterations for optimization-based approaches should only be viewed as a very rough estimate. optima than other style transfer objectives. This consistency property is advantageous when stylizing videos frame by frame, as our method is able to adapt to video without any explicit gluing procedure, such as using optical flow [22]. 4.1 Inverse Network Dataset and Training. We train the inversion network using the Microsoft COCO (MSCOCO) dataset [19] and a dataset of paintings sourced from wikiart.org and hosted by Kaggle [4]. Each dataset has roughly 80, 000 natural images and paintings, respectively. We train using Adam [15] for approximately 2 epochs on each dataset. We construct each minibatch using 2 natural images, 2 paintings, and 4 style-swapped activations using the images in the minibatch. Result. Figure 3 shows the approximation results for inverting style swapped activations with 3 3 patches. Though only trained on images of size , we achieve reasonable results for arbitrary full-sized images. We additionally compare against an inverse that has the same architecture but was not trained with the augmentation of style-swapped activations. As expected, the network that never sees style-swapped activations during training performs worse than the network with the augmented training set. Computation Time. Computation times for methods that can handle arbitary style images are shown in Table 1. Both our optimization-based and feedforward variants beat existing methods on speed while maintaining the same level of versatility. To the best of our knowledge, this is the first CNN-based feedforward approach that can generalize to any style image. Style Images: Content Ours Gatys et al. Content Ours Gatys et al. Figure 4: Qualitative examples of our method compared with Gatys et al. s formulation [9]. 4
5 References [1] Hussein A Aly and Eric Dubois. Image up-sampling using total-variation regularization with a new observation model. IEEE Transactions on Image Processing, 14(10): , [2] R. Collobert, K. Kavukcuoglu, and C. Farabet. Torch7: A matlab-like environment for machine learning. In BigLearn, NIPS Workshop, [3] Alexey Dosovitskiy and Thomas Brox. Inverting convolutional networks with convolutional networks. CoRR, abs/ , [4] Small Yellow Duck. Painter by numbers, wikiart.org. painter-by-numbers, [5] Alexei A Efros and William T Freeman. Image quilting for texture synthesis and transfer. In Proceedings of the 28th annual conference on Computer graphics and interactive techniques, pages ACM, [6] Alexei A Efros and Thomas K Leung. Texture synthesis by non-parametric sampling. In Computer Vision, The Proceedings of the Seventh IEEE International Conference on, volume 2, pages IEEE, [7] Michael Elad and Peyman Milanfar. Style-transfer via texture-synthesis. arxiv preprint arxiv: , [8] Oriel Frigo, Neus Sabater, Julie Delon, and Pierre Hellier. Split and match: Example-based adaptive patch sampling for unsupervised style transfer [9] Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge. A neural algorithm of artistic style. CoRR, abs/ , [10] Kun He, Yan Wang, and John E. Hopcroft. A powerful generative model using random weights for the deep image representation. CoRR, abs/ , [11] Aaron Hertzmann. Paint By Relaxation. Proceedings Computer Graphics International (CGI), pages 47 54, [12] Aaron Hertzmann, Charles E Jacobs, Nuria Oliver, Brian Curless, and David H Salesin. Image analogies. In Proceedings of the 28th annual conference on Computer graphics and interactive techniques, pages ACM, [13] Justin Johnson. neural-style [14] Justin Johnson, Alexandre Alahi, and Li Fei-Fei. Perceptual Losses for Real-Time Style Transfer and Super-Resolution. Arxiv, [15] Diederik Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arxiv preprint arxiv: , [16] Vivek Kwatra, Irfan Essa, Aaron Bobick, and Nipun Kwatra. Texture optimization for example-based synthesis. ACM Transactions on Graphics (ToG), 24(3): , [17] Chuan Li and Michael Wand. Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis. Cvpr 2016, page 9, [18] Lin Liang, Ce Liu, Ying-Qing Xu, Baining Guo, and Heung-Yeung Shum. Real-time texture synthesis by patch-based sampling. ACM Transactions on Graphics (ToG), 20(3): , [19] Tsung-Yi Lin, Michael Maire, Serge J. Belongie, Lubomir D. Bourdev, Ross B. Girshick, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C. Lawrence Zitnick. Microsoft COCO: common objects in context. CoRR, abs/ , [20] Peter Litwinowicz. Processing Images and Video for an Impressionist Effect. Proc. SIGGRAPH, pages , [21] Aravindh Mahendran and Andrea Vedaldi. Understanding deep image representations by inverting them. In 2015 IEEE conference on computer vision and pattern recognition (CVPR), pages IEEE, [22] Manuel Ruder, Alexey Dosovitskiy, and Thomas Brox. Artistic style transfer for videos. pages 1 14, [23] Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition. arxiv preprint arxiv: , [24] Dmitry Ulyanov, Vadim Lebedev, Andrea Vedaldi, and Victor Lempitsky. Texture Networks: Feed-forward Synthesis of Textures and Stylized Images. CoRR, [25] Dmitry Ulyanov, Andrea Vedaldi, and Victor S. Lempitsky. Instance normalization: The missing ingredient for fast stylization. CoRR, abs/ , [26] Li-Yi Wei and Marc Levoy. Fast texture synthesis using tree-structured vector quantization. In Proceedings of the 27th annual conference on Computer graphics and interactive techniques, pages ACM Press/Addison-Wesley Publishing Co.,
Decoder Network over Lightweight Reconstructed Feature for Fast Semantic Style Transfer
Decoder Network over Lightweight Reconstructed Feature for Fast Semantic Style Transfer Ming Lu 1, Hao Zhao 1, Anbang Yao 2, Feng Xu 3, Yurong Chen 2, and Li Zhang 1 1 Department of Electronic Engineering,
More informationConvolutional Neural Networks + Neural Style Transfer. Justin Johnson 2/1/2017
Convolutional Neural Networks + Neural Style Transfer Justin Johnson 2/1/2017 Outline Convolutional Neural Networks Convolution Pooling Feature Visualization Neural Style Transfer Feature Inversion Texture
More informationArbitrary Style Transfer in Real-Time with Adaptive Instance Normalization. Presented by: Karen Lucknavalai and Alexandr Kuznetsov
Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization Presented by: Karen Lucknavalai and Alexandr Kuznetsov Example Style Content Result Motivation Transforming content of an image
More informationMetaStyle: Three-Way Trade-Off Among Speed, Flexibility, and Quality in Neural Style Transfer
MetaStyle: Three-Way Trade-Off Among Speed, Flexibility, and Quality in Neural Style Transfer Chi Zhang and Yixin Zhu and Song-Chun Zhu {chizhang,yzhu,sczhu}@cara.ai International Center for AI and Robot
More informationExploring Style Transfer: Extensions to Neural Style Transfer
Exploring Style Transfer: Extensions to Neural Style Transfer Noah Makow Stanford University nmakow@stanford.edu Pablo Hernandez Stanford University pabloh2@stanford.edu Abstract Recent work by Gatys et
More informationarxiv: v1 [cs.cv] 22 Feb 2017
Synthesising Dynamic Textures using Convolutional Neural Networks arxiv:1702.07006v1 [cs.cv] 22 Feb 2017 Christina M. Funke, 1, 2, 3, Leon A. Gatys, 1, 2, 4, Alexander S. Ecker 1, 2, 5 1, 2, 3, 6 and Matthias
More informationTexture Synthesis. Darren Green (
Texture Synthesis Darren Green (www.darrensworld.com) 15-463: Computational Photography Alexei Efros, CMU, Fall 2005 Texture Texture depicts spatially repeating patterns Many natural phenomena are textures
More informationTexture Synthesis. Darren Green (
Texture Synthesis Darren Green (www.darrensworld.com) 15-463: Computational Photography Alexei Efros, CMU, Fall 2006 Texture Texture depicts spatially repeating patterns Many natural phenomena are textures
More informationUniversal Style Transfer via Feature Transforms
Universal Style Transfer via Feature Transforms Yijun Li UC Merced yli62@ucmerced.edu Chen Fang Adobe Research cfang@adobe.com Jimei Yang Adobe Research jimyang@adobe.com Zhaowen Wang Adobe Research zhawang@adobe.com
More informationCS 229 Final Report: Artistic Style Transfer for Face Portraits
CS 229 Final Report: Artistic Style Transfer for Face Portraits Daniel Hsu, Marcus Pan, Chen Zhu {dwhsu, mpanj, chen0908}@stanford.edu Dec 16, 2016 1 Introduction The goal of our project is to learn the
More informationCS231N Project Final Report - Fast Mixed Style Transfer
CS231N Project Final Report - Fast Mixed Style Transfer Xueyuan Mei Stanford University Computer Science xmei9@stanford.edu Fabian Chan Stanford University Computer Science fabianc@stanford.edu Tianchang
More informationarxiv: v2 [cs.cv] 11 Apr 2017
Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer Xin Wang 1,2, Geoffrey Oxholm 2, Da Zhang 1, Yuan-Fang Wang 1 arxiv:1612.01895v2 [cs.cv] 11 Apr 2017
More informationClassifying a specific image region using convolutional nets with an ROI mask as input
Classifying a specific image region using convolutional nets with an ROI mask as input 1 Sagi Eppel Abstract Convolutional neural nets (CNN) are the leading computer vision method for classifying images.
More informationMulti-style Transfer: Generalizing Fast Style Transfer to Several Genres
Multi-style Transfer: Generalizing Fast Style Transfer to Several Genres Brandon Cui Stanford University bcui19@stanford.edu Calvin Qi Stanford University calvinqi@stanford.edu Aileen Wang Stanford University
More informationGLStyleNet: Higher Quality Style Transfer Combining Global and Local Pyramid Features
GLStyleNet: Higher Quality Style Transfer Combining Global and Local Pyramid Features Zhizhong Wang*, Lei Zhao*, Wei Xing, Dongming Lu College of Computer Science and Technology, Zhejiang University {endywon,
More informationSON OF ZORN S LEMMA: TARGETED STYLE TRANSFER USING INSTANCE-AWARE SEMANTIC SEGMENTATION
SON OF ZORN S LEMMA: TARGETED STYLE TRANSFER USING INSTANCE-AWARE SEMANTIC SEGMENTATION Carlos Castillo, Soham De, Xintong Han, Bharat Singh, Abhay Kumar Yadav, and Tom Goldstein Department of Computer
More informationDiversified Texture Synthesis with Feed-forward Networks
Diversified Texture Synthesis with Feed-forward Networks Yijun Li 1, Chen Fang 2, Jimei Yang 2, Zhaowen Wang 2, Xin Lu 2, and Ming-Hsuan Yang 1 1 University of California, Merced 2 Adobe Research {yli62,mhyang}@ucmerced.edu
More informationData-driven methods: Video & Texture. A.A. Efros
Data-driven methods: Video & Texture A.A. Efros 15-463: Computational Photography Alexei Efros, CMU, Fall 2010 Michel Gondry train video http://youtube.com/watch?v=ques1bwvxga Weather Forecasting for Dummies
More informationGENERATIVE ADVERSARIAL NETWORK-BASED VIR-
GENERATIVE ADVERSARIAL NETWORK-BASED VIR- TUAL TRY-ON WITH CLOTHING REGION Shizuma Kubo, Yusuke Iwasawa, and Yutaka Matsuo The University of Tokyo Bunkyo-ku, Japan {kubo, iwasawa, matsuo}@weblab.t.u-tokyo.ac.jp
More informationReal-Time Neural Style Transfer for Videos
Real-Time Neural Style Transfer for Videos Haozhi Huang Hao Wang Wenhan Luo Lin Ma Wenhao Jiang Xiaolong Zhu Zhifeng Li Wei Liu Tsinghua University Tencent AI Lab Correspondence: huanghz08@gmail.com wliu@ee.columbia.edu
More informationarxiv: v1 [cs.cv] 14 Jun 2017
Photo-realistic Facial Texture Transfer Parneet Kaur Hang Zhang Kristin Dana arxiv:706.0306v [cs.cv] Jun 207 Department of Electrical and Computer Engineering, Rutgers University, New Brunswick, USA parneet@rutgers.edu,
More informationA Neural Algorithm of Artistic Style. Leon A. Gatys, Alexander S. Ecker, Mattthias Bethge Presented by Weidi Xie (1st Oct 2015 )
A Neural Algorithm of Artistic Style Leon A. Gatys, Alexander S. Ecker, Mattthias Bethge Presented by Weidi Xie (1st Oct 2015 ) What does the paper do? 2 Create artistic images of high perceptual quality.
More informationA Neural Algorithm of Artistic Style. Leon A. Gatys, Alexander S. Ecker, Matthias Bethge
A Neural Algorithm of Artistic Style Leon A. Gatys, Alexander S. Ecker, Matthias Bethge Presented by Shishir Mathur (1 Sept 2016) What is this paper This is the research paper behind Prisma It creates
More informationDOMAIN-ADAPTIVE GENERATIVE ADVERSARIAL NETWORKS FOR SKETCH-TO-PHOTO INVERSION
DOMAIN-ADAPTIVE GENERATIVE ADVERSARIAL NETWORKS FOR SKETCH-TO-PHOTO INVERSION Yen-Cheng Liu 1, Wei-Chen Chiu 2, Sheng-De Wang 1, and Yu-Chiang Frank Wang 1 1 Graduate Institute of Electrical Engineering,
More informationData-driven methods: Video & Texture. A.A. Efros
Data-driven methods: Video & Texture A.A. Efros CS194: Image Manipulation & Computational Photography Alexei Efros, UC Berkeley, Fall 2014 Michel Gondry train video http://www.youtube.com/watch?v=0s43iwbf0um
More informationDOMAIN-ADAPTIVE GENERATIVE ADVERSARIAL NETWORKS FOR SKETCH-TO-PHOTO INVERSION
2017 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING, SEPT. 25 28, 2017, TOKYO, JAPAN DOMAIN-ADAPTIVE GENERATIVE ADVERSARIAL NETWORKS FOR SKETCH-TO-PHOTO INVERSION Yen-Cheng Liu 1,
More informationSpatial Control in Neural Style Transfer
Spatial Control in Neural Style Transfer Tom Henighan Stanford Physics henighan@stanford.edu Abstract Recent studies have shown that convolutional neural networks (convnets) can be used to transfer style
More informationArbitrary Style Transfer in Real-time with Adaptive Instance Normalization
Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization Xun Huang Serge Belongie Department of Computer Science & Cornell Tech, Cornell University {xh58,sjb344}@cornell.edu Abstract
More informationShow, Discriminate, and Tell: A Discriminatory Image Captioning Model with Deep Neural Networks
Show, Discriminate, and Tell: A Discriminatory Image Captioning Model with Deep Neural Networks Boya Peng Department of Computer Science Stanford University boya@stanford.edu Zelun Luo Department of Computer
More informationTexture Synthesis Through Convolutional Neural Networks and Spectrum Constraints
Texture Synthesis Through Convolutional Neural Networks and Spectrum Constraints Gang Liu, Yann Gousseau Telecom-ParisTech, LTCI CNRS 46 Rue Barrault, 75013 Paris, France. {gang.liu, gousseau}@telecom-paristech.fr
More informationTexture Synthesis and Manipulation Project Proposal. Douglas Lanman EN 256: Computer Vision 19 October 2006
Texture Synthesis and Manipulation Project Proposal Douglas Lanman EN 256: Computer Vision 19 October 2006 1 Outline Introduction to Texture Synthesis Previous Work Project Goals and Timeline Douglas Lanman
More informationREGION AVERAGE POOLING FOR CONTEXT-AWARE OBJECT DETECTION
REGION AVERAGE POOLING FOR CONTEXT-AWARE OBJECT DETECTION Kingsley Kuan 1, Gaurav Manek 1, Jie Lin 1, Yuan Fang 1, Vijay Chandrasekhar 1,2 Institute for Infocomm Research, A*STAR, Singapore 1 Nanyang Technological
More informationAdmin. Data driven methods. Overview. Overview. Parametric model of image patches. Data driven (Non parametric) Approach 3/31/2008
Admin Office hours straight after class today Data driven methods Assignment 3 out, due in 2 weeks Lecture 8 Projects.. Overview Overview Texture synthesis Quilting Image Analogies Super resolution Scene
More informationCSCI 1290: Comp Photo
CSCI 1290: Comp Photo Fall 2018 @ Brown University James Tompkin Many slides thanks to James Hays old CS 129 course, along with all of its acknowledgements. Smartphone news Qualcomm Snapdragon 675 just
More informationUnsupervised domain adaptation of deep object detectors
Unsupervised domain adaptation of deep object detectors Debjeet Majumdar 1 and Vinay P. Namboodiri2 Indian Institute of Technology, Kanpur - Computer Science and Engineering Kalyanpur, Kanpur, Uttar Pradesh
More informationTexture. CS 419 Slides by Ali Farhadi
Texture CS 419 Slides by Ali Farhadi What is a Texture? Texture Spectrum Steven Li, James Hays, Chenyu Wu, Vivek Kwatra, and Yanxi Liu, CVPR 06 Texture scandals!! Two crucial algorithmic points Nearest
More informationarxiv: v1 [cs.cv] 5 May 2017
Characterizing and Improving Stability in Neural Transfer Agrim Gupta, Justin Johnson, Alexandre Alahi, and Li Fei-Fei Department of Computer Science, Stanford University agrim@stanford.edu {jcjohns,alahi,feifeili}@cs.stanford.edu
More informationArtistic style transfer for videos
Artistic style transfer for videos Manuel Ruder, Alexey Dosovitskiy, Thomas Brox Department of Computer Science University of Freiburg {rudera, dosovits, brox}@cs.uni-freiburg.de arxiv:1604.08610v1 [cs.cv]
More informationarxiv: v2 [cs.cv] 13 Jun 2017
Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN arxiv:1706.03319v2 [cs.cv] 13 Jun 2017 Lvmin Zhang, Yi Ji and Xin Lin School of Computer Science and Technology,
More informationGenerative Networks. James Hays Computer Vision
Generative Networks James Hays Computer Vision Interesting Illusion: Ames Window https://www.youtube.com/watch?v=ahjqe8eukhc https://en.wikipedia.org/wiki/ames_trapezoid Recap Unsupervised Learning Style
More informationShow, Discriminate, and Tell: A Discriminatory Image Captioning Model with Deep Neural Networks
Show, Discriminate, and Tell: A Discriminatory Image Captioning Model with Deep Neural Networks Zelun Luo Department of Computer Science Stanford University zelunluo@stanford.edu Te-Lin Wu Department of
More information+ = The Goal of Texture Synthesis. Image Quilting for Texture Synthesis & Transfer. The Challenge. Texture Synthesis for Graphics
Image Quilting for Texture Synthesis & Transfer Alexei Efros (UC Berkeley) Bill Freeman (MERL) The Goal of Texture Synthesis True (infinite) texture input image SYNTHESIS generated image Given a finite
More informationTopics. Image Processing Techniques and Smart Image Manipulation. Texture Synthesis. Topics. Markov Chain. Weather Forecasting for Dummies
Image Processing Techniques and Smart Image Manipulation Maneesh Agrawala Topics Texture Synthesis High Dynamic Range Imaging Bilateral Filter Gradient-Domain Techniques Matting Graph-Cut Optimization
More informationVolume Editor. Hans Weghorn Faculty of Mechatronics BA-University of Cooperative Education, Stuttgart Germany
Volume Editor Hans Weghorn Faculty of Mechatronics BA-University of Cooperative Education, Stuttgart Germany Proceedings of the 4 th Annual Meeting on Information Technology and Computer Science ITCS,
More informationNeural style transfer
1/32 Neural style transfer Victor Kitov v.v.kitov@yandex.ru 2/32 Neural style transfer Input: content image, style image. Style transfer - application of artistic style from style image to content image.
More informationarxiv: v2 [cs.cv] 14 Jul 2018
Constrained Neural Style Transfer for Decorated Logo Generation arxiv:1803.00686v2 [cs.cv] 14 Jul 2018 Gantugs Atarsaikhan, Brian Kenji Iwana, Seiichi Uchida Graduate School of Information Science and
More informationHelsinki University of Technology Telecommunications Software and Multimedia Laboratory T Seminar on computer graphics Spring 2004
Helsinki University of Technology 29.3.2004 Telecommunications Software and Multimedia Laboratory T-111.500 Seminar on computer graphics Spring 2004 Image Analogies Jari Huttunen 48120P Image Analogies
More informationImproving Semantic Style Transfer Using Guided Gram Matrices
Improving Semantic Style Transfer Using Guided Gram Matrices Chung Nicolas 1,2, Rong Xie 1,2, Li Song 1,2, and Wenjun Zhang 1,2 1 Institute of Image Communication and Network Engineering, Shanghai Jiao
More informationSupplementary Material: Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos
Supplementary Material: Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos Kihyuk Sohn 1 Sifei Liu 2 Guangyu Zhong 3 Xiang Yu 1 Ming-Hsuan Yang 2 Manmohan Chandraker 1,4 1 NEC Labs
More informationDepth-aware Neural Style Transfer
Depth-aware Neural Style Transfer Yu-Kun Lai Paul L. Rosin Xiao-Chang Liu Ming-Ming Cheng CCCE, Nankai University (a) Style: The Muse by Pablo Picasso Cardiff University (b) Content (from Pixabay) (c)
More informationCSE 559A: Computer Vision
CSE 559A: Computer Vision Fall 2018: T-R: 11:30-1pm @ Lopata 101 Instructor: Ayan Chakrabarti (ayan@wustl.edu). Course Staff: Zhihao Xia, Charlie Wu, Han Liu http://www.cse.wustl.edu/~ayan/courses/cse559a/
More informationPhotorealistic Style Transfer with Screened Poisson Equation
MECHREZ et al.: SCREENED POISSON FOR PHOTOREALISTIC STYLE TRANSFER 1 Photorealistic Style Transfer with Screened Poisson Equation Roey Mechrez 1 http://cgm.technion.ac.il/people/roey/ Eli Shechtman 2 research.adobe.com/person/eli-shechtman/
More informationPredicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture David Eigen, Rob Fergus
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture David Eigen, Rob Fergus Presented by: Rex Ying and Charles Qi Input: A Single RGB Image Estimate
More informationarxiv: v2 [cs.cv] 22 May 2018
Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration Lu Sheng 1, Ziyi Lin 2, Jing Shao 2, Xiaogang Wang 1 1 CUHK-SenseTime Joint Lab, The Chinese University of Hong Kong 2 SenseTime Research
More informationTexture attribute synthesis and transfer using feed-forward CNNs
Texture attribute synthesis and transfer using feed-forward CNNs Thomas Irmer Ruhr University Bochum thomas.irmer@rub.de Tobias Glasmachers Ruhr University Bochum tobias.glasmachers@ini.rub.de Subhransu
More informationMedian filter. Non-linear filtering example. Degraded image. Radius 1 median filter. Today
Today Non-linear filtering example Median filter Replace each pixel by the median over N pixels (5 pixels, for these examples). Generalizes to rank order filters. In: In: 5-pixel neighborhood Out: Out:
More informationNon-linear filtering example
Today Non-linear filtering example Median filter Replace each pixel by the median over N pixels (5 pixels, for these examples). Generalizes to rank order filters. In: In: 5-pixel neighborhood Out: Out:
More informationComputation-Performance Optimization of Convolutional Neural Networks with Redundant Kernel Removal
Computation-Performance Optimization of Convolutional Neural Networks with Redundant Kernel Removal arxiv:1705.10748v3 [cs.cv] 10 Apr 2018 Chih-Ting Liu, Yi-Heng Wu, Yu-Sheng Lin, and Shao-Yi Chien Media
More informationImage Captioning with Attention
ing with Attention Blaine Rister (blaine@stanford.edu), Dieterich Lawson (jdlawson@stanford.edu) 1. Introduction In the past few years, neural networks have fueled dramatic advances in image classication.
More informationChannel Locality Block: A Variant of Squeeze-and-Excitation
Channel Locality Block: A Variant of Squeeze-and-Excitation 1 st Huayu Li Northern Arizona University Flagstaff, United State Northern Arizona University hl459@nau.edu arxiv:1901.01493v1 [cs.lg] 6 Jan
More informationPerceptual Loss for Convolutional Neural Network Based Optical Flow Estimation. Zong-qing LU, Xiang ZHU and Qing-min LIAO *
2017 2nd International Conference on Software, Multimedia and Communication Engineering (SMCE 2017) ISBN: 978-1-60595-458-5 Perceptual Loss for Convolutional Neural Network Based Optical Flow Estimation
More informationarxiv: v1 [cs.gr] 15 Jan 2019
Image Synthesis and Style Transfer Somnuk Phon-Amnuaisuk 1,2 arxiv:1901.04686v1 [cs.gr] 15 Jan 2019 Media Informatics Special Interest Group, 1 Centre for Innovative Engineering, Universiti Teknologi Brunei,
More informationarxiv: v2 [cs.gr] 1 Feb 2017
Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses arxiv:1701.08893v2 [cs.gr] 1 Feb 2017 Eric Risser1, Pierre Wilmot1, Connelly Barnes1,2 1 Artomatix, 2 University
More informationMore details on presentations
More details on presentations Aim to speak for ~50 min (after 15 min review, leaving 10 min for discussions) Try to plan discussion topics It s fine to steal slides from the Web, but be sure to acknowledge
More informationarxiv: v1 [cs.cv] 26 Jul 2016
Semantic Image Inpainting with Perceptual and Contextual Losses arxiv:1607.07539v1 [cs.cv] 26 Jul 2016 Raymond Yeh Chen Chen Teck Yian Lim, Mark Hasegawa-Johnson Minh N. Do Dept. of Electrical and Computer
More informationDeep Learning. Vladimir Golkov Technical University of Munich Computer Vision Group
Deep Learning Vladimir Golkov Technical University of Munich Computer Vision Group 1D Input, 1D Output target input 2 2D Input, 1D Output: Data Distribution Complexity Imagine many dimensions (data occupies
More informationarxiv: v1 [cs.cv] 5 Mar 2016 Abstract
Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artwork Alex J. Champandard nucl.ai Research Laboratory alexjc@nucl.ai nucl.ai Conference 2016 Artificial Intelligence in Creative Industries
More informationExample-Based Image Super-Resolution Techniques
Example-Based Image Super-Resolution Techniques Mark Sabini msabini & Gili Rusak gili December 17, 2016 1 Introduction With the current surge in popularity of imagebased applications, improving content
More informationAvatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration
Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration Lu Sheng 1, Ziyi Lin 2, Jing Shao 2, Xiaogang Wang 1 1 CUHK-SenseTime Joint Lab, The Chinese University of Hong Kong 2 SenseTime Research
More informationarxiv: v3 [cs.cv] 22 Feb 2018
A Closed-form Solution to Photorealistic Image Stylization Yijun Li 1, Ming-Yu Liu 2, Xueting Li 1, Ming-Hsuan Yang 1,2, and Jan Kautz 2 1 University of California, Merced 2 NVIDIA {yli62,xli75,mhyang}@ucmerced.edu
More informationA Pragmatic AI Approach to Creating Artistic Visual Variations by Neural Style Transfer
A Pragmatic AI Approach to Creating Artistic Visual Variations by Neural Style Transfer Chaehan So International Design School for Advanced Studies, Design Psychology Lab, Hongik University, Seoul, South
More informationCS230: Lecture 3 Various Deep Learning Topics
CS230: Lecture 3 Various Deep Learning Topics Kian Katanforoosh, Andrew Ng Today s outline We will learn how to: - Analyse a problem from a deep learning approach - Choose an architecture - Choose a loss
More informationA Closed-form Solution to Photorealistic Image Stylization
A Closed-form Solution to Photorealistic Image Stylization Yijun Li 1, Ming-Yu Liu 2, Xueting Li 1, Ming-Hsuan Yang 1,2, Jan Kautz 2 1 University of California, Merced 2 NVIDIA {yli62,xli75,mhyang}@ucmerced.edu
More informationABSTRACT Departures from a regular texture pattern can happen in many different dimensions. Previous related work has focused on faithful texture synt
Deformable Texture: the Irregular-Regular-Irregular Cycle Yanxi Liu and Wen-Chieh Lin CMU-RI-TR-03-26 The Robotics Institute Carnegie Mellon University Pittsburgh, PA 15213 cfl2003 Carnegie Mellon University
More informationTowards End-to-End Audio-Sheet-Music Retrieval
Towards End-to-End Audio-Sheet-Music Retrieval Matthias Dorfer, Andreas Arzt and Gerhard Widmer Department of Computational Perception Johannes Kepler University Linz Altenberger Str. 69, A-4040 Linz matthias.dorfer@jku.at
More informationSemantic Soft Segmentation Supplementary Material
Semantic Soft Segmentation Supplementary Material YAĞIZ AKSOY, MIT CSAIL and ETH Zürich TAE-HYUN OH, MIT CSAIL SYLVAIN PARIS, Adobe Research MARC POLLEFEYS, ETH Zürich and Microsoft WOJCIECH MATUSIK, MIT
More informationCOMP9444 Neural Networks and Deep Learning 7. Image Processing. COMP9444 c Alan Blair, 2017
COMP9444 Neural Networks and Deep Learning 7. Image Processing COMP9444 17s2 Image Processing 1 Outline Image Datasets and Tasks Convolution in Detail AlexNet Weight Initialization Batch Normalization
More informationRecovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform. Xintao Wang Ke Yu Chao Dong Chen Change Loy
Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform Xintao Wang Ke Yu Chao Dong Chen Change Loy Problem enlarge 4 times Low-resolution image High-resolution image Previous
More informationVideo Generation Using 3D Convolutional Neural Network
Video Generation Using 3D Convolutional Neural Network Shohei Yamamoto Grad. School of Information Science and Technology The University of Tokyo yamamoto@mi.t.u-tokyo.ac.jp Tatsuya Harada Grad. School
More informationarxiv: v4 [cs.cv] 27 Jul 2018
Neural Stereoscopic Image Style Transfer Xinyu Gong Haozhi Huang Lin Ma Fumin Shen Wei Liu Tong Zhang {neoxygong,huanghz08,forest.linma,fumin.shen}@gmail.com wl2223@columbia.edu tongzhang@tongzhang-ml.org
More informationRecovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform Supplementary Material
Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform Supplementary Material Xintao Wang 1 Ke Yu 1 Chao Dong 2 Chen Change Loy 1 1 CUHK - SenseTime Joint Lab, The Chinese
More informationCartoonGAN: Generative Adversarial Networks for Photo Cartoonization
CartoonGAN: Generative Adversarial Networks for Photo Cartoonization Yang Chen Tsinghua University, China chenyang15@mails.tsinghua.edu.cn Yu-Kun Lai Cardiff University, UK Yukun.Lai@cs.cf.ac.uk Yong-Jin
More informationDeep Learning in Visual Recognition. Thanks Da Zhang for the slides
Deep Learning in Visual Recognition Thanks Da Zhang for the slides Deep Learning is Everywhere 2 Roadmap Introduction Convolutional Neural Network Application Image Classification Object Detection Object
More informationarxiv: v2 [cs.cv] 11 Sep 2018
Neural omic tyle Transfer: ase tudy Maciej Pęśko and Tomasz Trzciński Warsaw University of Technology, Warsaw, Poland, mpesko@mion.elka.pw.edu.pl t.trzcinski@ii.pw.edu.pl, arxiv:1809.01726v2 [cs.v] 11
More informationarxiv: v2 [cs.cv] 23 Dec 2017
TextureGAN: Controlling Deep Image Synthesis with Texture Patches Wenqi Xian 1 Patsorn Sangkloy 1 Varun Agrawal 1 Amit Raj 1 Jingwan Lu 2 Chen Fang 2 Fisher Yu 3 James Hays 1 1 Georgia Institute of Technology
More informationTexture Synthesis with Spatial Generative Adversarial Networks
Texture Synthesis with Spatial Generative Adversarial Networks Nikolay Jetchev Urs Bergmann Roland Vollgraf Zalando Research {nikolay.jetchev,urs.bergmann,roland.vollgraf}@zalando.de 1 Abstract Generative
More informationFigure 1: A sampler of different types of textures. Figure 2: Left: An irregular texture overlaid with its lattice. Right: its near-regular counterpar
Deformable Texture: the Irregular-Regular-Irregular Cycle Yanxi Liu and Wen-Chieh Lin The Robotics Institute, Carnegie Mellon University, 5000 Forbes Ave. Pittsburgh, PA 15213 fyanxi,wcling@cs.cmu.edu
More informationUnsupervised Deep Learning. James Hays slides from Carl Doersch and Richard Zhang
Unsupervised Deep Learning James Hays slides from Carl Doersch and Richard Zhang Recap from Previous Lecture We saw two strategies to get structured output while using deep learning With object detection,
More informationCharacterizing and Improving Stability in Neural Style Transfer
Characterizing and Improving Stability in Neural Transfer Agrim Gupta 1 Justin Johnson 1 Alexandre Alahi 1,2 Li Fei-Fei 1 Stanford University 1 École Polytechnique Fédérate de Lausanne 2 Abstract Recent
More informationFace Sketch Synthesis with Style Transfer using Pyramid Column Feature
Face Sketch Synthesis with Style Transfer using Pyramid Column Feature Chaofeng Chen 1, Xiao Tan 2, and Kwan-Yee K. Wong 1 1 The University of Hong Kong, 2 Baidu Research {cfchen, kykwong}@cs.hku.hk, tanxchong@gmail.com
More informationarxiv: v1 [cs.cv] 26 May 2017
arxiv:1705.09587v1 [cs.cv] 26 May 2017 J. JEONG, H. PARK AND N. KWAK: UNDER REVIEW IN BMVC 2017 1 Enhancement of SSD by concatenating feature maps for object detection Jisoo Jeong soo3553@snu.ac.kr Hyojin
More informationMulti-Glance Attention Models For Image Classification
Multi-Glance Attention Models For Image Classification Chinmay Duvedi Stanford University Stanford, CA cduvedi@stanford.edu Pararth Shah Stanford University Stanford, CA pararth@stanford.edu Abstract We
More informationWhat was Monet seeing while painting? Translating artworks to photo-realistic images M. Tomei, L. Baraldi, M. Cornia, R. Cucchiara
What was Monet seeing while painting? Translating artworks to photo-realistic images M. Tomei, L. Baraldi, M. Cornia, R. Cucchiara COMPUTER VISION IN THE ARTISTIC DOMAIN The effectiveness of Computer Vision
More informationStructured Prediction using Convolutional Neural Networks
Overview Structured Prediction using Convolutional Neural Networks Bohyung Han bhhan@postech.ac.kr Computer Vision Lab. Convolutional Neural Networks (CNNs) Structured predictions for low level computer
More informationComputer Vision: Homework 5 Optical Character Recognition using Neural Networks
16-720 Computer Vision: Homework 5 Optical Character Recognition using Neural Networks Instructors: Deva Ramanan TAs: Achal Dave*, Sashank Jujjavarapu, Siddarth Malreddy, Brian Pugh Originally developed
More informationarxiv: v1 [cs.cv] 1 Dec 2017
GANosaic: Mosaic Creation with Generative Texture Manifolds Nikolay Jetchev nikolay.jetchev@zalando.de Zalando Research Urs Bergmann urs.bergmann@zalando.de Zalando Research Calvin Seward calvin.seward@zalando.de
More informationarxiv: v2 [cs.cv] 21 May 2018
Learning Selfie-Friendly Abstraction from Artistic Style Images Yicun Liu Jimmy Ren Jianbo Liu Jiawei Zhang Xiaohao Chen SenseTime Research {liuyicun,rensijie,liujianbo,zhangjiawei,chenxiaohao}@sensetime.com
More informationControlling Perceptual Factors in Neural Style Transfer
Controlling Perceptual Factors in Neural Style Transfer Leon A. Gatys 1 Alexander S. Ecker 1 Matthias Bethge 1 Aaron Hertzmann 2 Eli Shechtman 2 1 University of Tübingen 2 Adobe Research (a) Content (b)
More informationAn Improved Texture Synthesis Algorithm Using Morphological Processing with Image Analogy
An Improved Texture Synthesis Algorithm Using Morphological Processing with Image Analogy Jiang Ni Henry Schneiderman CMU-RI-TR-04-52 October 2004 Robotics Institute Carnegie Mellon University Pittsburgh,
More informationEnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis Supplementary
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis Supplementary Mehdi S. M. Sajjadi Bernhard Schölkopf Michael Hirsch Max Planck Institute for Intelligent Systems Spemanstr.
More information