图像处理相关的论文

2018-01-11 19:03:30 wzy_zju 阅读数 5294


      一: 去雾方面的论文

           1、Efficient Image Dehazing with Boundary Constraint and Contextual Regularization,下载地址:

           http://lab.datatang.com/1984DA173065/WebFile/DocWeb/2014012053738649.pdf

 

          效果:

    

     2、 Fast image dehazing using guided joint bilateral filter

         http://graphvision.whu.edu.cn/papers/cgi2012.pdf

      效果:

      3、Fast Haze Removal Algorithm for Surveillance Video   这是一篇讲如何对视频进行快速去雾的文章,没涉及到具体的算法,不过可以看看。

     二、双边滤波

   1、Recursive Bilateral Filtering ,这个在杨庆雄的网站里有下载:http://www.cs.cityu.edu.hk/~qiyang/,他的个人网站下还有好多其他的论文和算法下载。

        该算法速度非常快,但是效果有点瑕疵。

    三、单幅图像的高光去除

  1、Real-Time Specular Highlight Removal Using Bilateral Filtering

      2、Real-time highlight removal using intensity ratio

      3、Separating Reflection Components of Textured Surfaces Using a Single Image

    四、水下图像增强

  1、Enhancing Underwater Images and Videos by Fusion,这是一篇通过融合技术来增强图像的文章,虽然不是很复杂,但是文章的思路应该能广泛应用,这也是我今年重点研究何实现的文章之一。

      下载:http://research.edm.uhasselt.be/~oancuti/Underwater_CVPR_2012/

      效果:

   

 

    如上图所示,该算法还具有较强的去雾能力。

2015-04-03 21:45:09 zy122121cs 阅读数 14690

Colorization and Color Transfer(图像上色和颜色迁移)

Semantic Colorization with Internet Images, Chia et al. SIGGRAPH ASIA 2011
Color Harmonization, Cohen-Or, Sorkine, Gal, Leyvand, and Xu. Web Page
Computing the alpha-Channel with Probabilistic Segmentation for Image Colorization, Dalmau-Cedeno, Rivera, and Mayorga
Bayesian Color Constancy Revisited, Gehler, Rother, Blake, Minka, and Sharp
Color2Gray: Salience-Preserving Color Removal, Gooch, Olsen, Tumblin, and Gooch
Color Conceptualization, Hou and Zhang
Light Mixture Estimation for Spatially Varying White Balance, Hsu, Mertens, Paris, Avidan, and Durand. Web Page
Bayesian Correction of Image Intensity with Spatial Consideration, Jia, Sun, Tang, and Shum
Robust Color-to-gray via Nonlinear Global Mapping, Kim, Jang, Demouth, and Lee. SIGGRAPH Asia 2009 Web Page
Variational Models for Image Colorization via Chromaticity and Brightness Decomposition, Kang and March
Colorization using Optimization, Levin, Lischinski, and Weiss
Intrinsic Colorization, Liu et al. SIGGRAPH ASIA 2008 Web Page
N-Dimensional Probability Density Function Transfer and Its Application to Colour Transfer, Pitie et al.
Automated Colour Grading using Colour Distribution Transfer, Pitie et al.
Color by Linear Neighborhood Embedding, Qiu and Guan
Manga Colorization, Qu, Wong, and Heng
Color Transfer between Images, Reinhard, Ashikhmin, Gooch, and Shirley
Local Color Transfer via Probabilistic Segmentation by Expectation-Maximization, Tai, Jia, and Tang
Data-Driven Image Color Theme Enhancement, Wang, Yu, Wong, Chen, and Xu. SIGGRAPH Asia 2010 Web Page
Color Transfer in Correlated Color Space, Xiao and Ma
Fast Image and Video Colorization using Chrominance Blending, Yatziv and Sapiro

Texture Synthesis and Inpainting(纹理和成和修复)

Seam Carving for Content-Aware Image Resizing, Avidan and Shamir. Wikipedia
Synthesizing Natural Textures, Ashikhmin
PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing, Barnes, Shechtman, Finkelstein, and Goldman. SIGGRAPH 2009. Web Page
Image Inpainting, Bertalmio, Sapiro, Caselles, and Ballester
Video Watercolorization using Bidirectional Texture Advection, Bousseau, Neyret, Thollot, and Salesin
Camouflage Images, Chu et al. SIGGRAPH 2010 Web Page
Object Removal by Exemplar-Based Inpainting, Criminisi, Perez, and Toyama
Weiming DONG's web page contains useful information about texture synthesis and image resizing
Image Quilting for Texture Synthesis and Transfer, Efros and Freeman
Texture Synthesis by Non-parametric Sampling, Efros and Leung
RotoTexture: Automated Tools for Texturing Raw Video, Fang and Hart
Textureshop: Texture Synthesis as a Photograph Editing Tool, Fang and Hart
Multiscale Texture Synthesis, Han, Risser, Ramamoorthi, and Grinspun
Scene Completion Using Millions of Photographs, Hays and Efros
Image Analogies, Hertzmann, Jacobs, Oliver, Curless, and Salesin
Graphcut Textures: Image and Video Synthesis Using Graph Cuts, Kwatra , Schodl , Essa , Turk, and Bobick
Improved Seam Carving for Video Retargeting, Rubinstein, Shamir, and Avidan. Video
Multi-operator Media Retargeting, Rubinstein, Shamir, and Avidan. SIGGRAPH 2009. Web Page
Fields of Experts: A Framework for Learning Image Priors, Roth and Black
Curvature Regularity for Region-based Image Segmentation and Inpainting: A Linear Programming Relaxation, Schoenemann, Kahl, and Cremers. ICCV 2009.
Fast Texture Synthesis using Tree-structured Vector Quantization, Wei and Levoy
Non-homogeneous Content-driven Video-retargeting, Wolf, Guttmann, and Cohen-Or
Feature Matching and Deformation for Texture Synthesis, Wu and Yu

HDR and Tone Mapping(高动态范围成像和色调映射)

Do HDR Displays Support LDR Content? A Psychophysical Evaluation, Akyu"z, Reinhard, Fleming, Riecke, Bu"lthoff
Two-scale Tone Management for Photographic Look, Bae, Paris, and Durand
Real-time Edge-Aware Image Processing with the Bilateral Grid, Chen, Paris, Durand
Recovering High Dynamic Range Radiance Maps from Photographs, Debevec and Malik
Fast Bilateral Filtering for the Display of High-Dynamic-Range Images, Durand and Dorsey
Edge-Preserving Decompositions for Multi-Scale Tone and Detail Manipulation, Farbman, Fattal, Lischinski, and Szeliski. SIGGRAPH 2009. Web Page
Optimal HDR reconstruction with linear digital cameras, Granados et al., CVPR 2010.
Gradient Domain High Dynamic Range Compression, Fattal, Lischinski, and Werman
Modeling Human Color Perception under Extended Luminance Levels, Kim, Weyrich, and Kautz. SIGGRAPH 2009. Web Page
Perceptually Based Tone Mapping for Low-Light Conditions, Kirk and O'Brien. SIGGRAPH 2011. Web Page
Compressing and Companding High Dynamic Range Images with Subband Architectures, Li, Sharan, and Adelson
Radiometric Calibration Using a Single Image Lin, Gu, Yamazaki, and Shum
Determining the Radiometric Response Function from a Single Grayscale Image, Lin and Zhang
Interactive Local Adjustment of Tonal Values, Lischinski, Farbman, Uyttendaele, and Szeliski. Web Page
Exposure Fusion, Mertens, Kautz, Van Reeth
Radiometric Self Calibration, Mitsunaga and Nayar
Photographic Tone Reproduction for Digital Images, Reinhard, Stark, Shirley and Ferwerda
Ldr2Hdr: On-the-Fly Reverse Tone Mapping of Legacy Video and Photographs, Rempel, Trentacoste, Seetzen, Young, Heidrich, Whitehead, and Ward
High Dynamic Range Image Hallucination, Wang, Wei, Zhou, Guo, and Shum
Fast, Robust Image Registration for Compositing High Dynamic Range Photographs from Hand-Held Exposures, Ward

Intrinsic Images(本征图像)

Removing Photography Artifacts using Gradient Projection and Flash-Exposure Sampling, Agrawal, Raskar, Nayar, and Li
User-Assisted Intrinsic Images, Bousseau, Paris, and Durand. SIGGRAPH Asia 2009. Web Page
Flash Photography Enhancement via Intrinsic Relighting, Eisemann and Durand
Bayesian Model of Surface Perception, Freeman and Viola
Detecting Illumination in Images, Finlayson, Fredembach, and Drew
Ground Truth Dataset and Baseline Evaluations for Intrinsic Image AlgorithmsGrosse, Johnson, Adelson, and Freeman. ICCV 2009.
A Variational Framework for Retinex, Kimmel, Elad, Shaked, Keshet, and Sobel
Dark Flash Photography, Krishnan amd Fergus. SIGGRAPH 2009. Web Page
Lightness and Retinex Theory, Land and McCann
Estimating Intrinsic Images from Image Sequenceswith Biased Illumination, Matsushita, Lin, Kang, Shum. ECCV 2004
Post-production Facial Performance Relighting using Reflectance Transfer, Peers, Tamura, Matusik, and Debevec
Separation of Highlight Reflections from Textured Surfaces, Tan, Lin, and Quan
Recovering Intrinsic Images from a Single Image, Tappen, Freeman, and Adelson
Estimating Intrinsic Component Images using Non-Linear Regression, Tappen, Adelson, and Freeman
Deriving Intrinsic Images from Image Sequences, Weiss

Deblurring, Denoising, and Super-Resolution(图像去模糊,去噪和超分辨率)

Reinterpretable Imager: Towards Variable Post Capture Space, Angle & Time Resolution in Photography, Agrawal, Veeraraghavan, and Raskar. Eurographics 2010.
Invertible Motion Blur in Video, Agrawal, Xu, and Raskar. SIGGRAPH 2009.
Optimal Single Image Capture for Motion Deblurring, Agrawal and Raskar. CVPR 2009.
Coded Exposure Deblurring: Optimized Codes for PSF Estimation and Invertibility, Agrawal and Xu. CVPR 2009.
A Non-local Algorithm for Image Denoising, Buades, Coll, and Morel.
Analyzing Spatially-varying Blur, Chakrabarti, Zickler, and Freeman. CVPR 2010.
Fast Motion Deblurring, Cho and Lee. SIGGRAPH Asia 2009. Web Page
Motion Blur Removal with Orthogonal Parabolic Exposures, Cho, Levin, Durand, and Freeman. CVPR 2010. Web Page
Handling Outliers in Non-Blind Image Deconvolution, Cho, Wang, and Lee. ICCV 2011. Web Page
Display supersampling, Damera-Venkata and Chang
Image Upsampling Via Imposed Edge Statistics, Fattal
Single Image Dehazing, Fattal.    Web Page   Demo Code
Multiscale Shape and Detail Enhancement from Multi-light Image Collections, Fattal, Agrawala, and Rusinkiewicz
Removing Camera Shake from a Single Image, Fergus, Singh, Hertzmann, Roweis, and Freeman
Example-Based Super-Resolution, Freeman, Jones, and Pasztor
Space-Variant Single-Image Blind Deconvolution for Removing Camera Shake, Harmeling, Hirsch, and Scholkopf
Multiframe Blind Deconvolution, Super-Resolution, and Saturation Correction via Incremental EM, Harmeling, Sra, Hirsch, and Scholkopf
Single Image Haze Removal Using Dark Channel Prior, He, Sun, Tang. CVPR 2009.
Image Deblurring and Denoising using Color Priors, Joshi, Zitnick, Szeliski, and Kriegman. CVPR 2009. Web Page
Image Deblurring using Inertial Measurement Sensors, Joshi, Kang, Zitnick, and Szeliski. SIGGRAPH 2010. Web Page
Joint Bilateral Upsampling, Kopf, Cohen, Lischinski, Uyttendaele
Blind Deconvolution using a Normalized Sparsity Measure, Krishnan, Tay, and Fergus. CVPR 2011. Web Page
Blind Motion Deblurring Using Image Statistics, Levin
Image and Depth from a Conventional Camera with a Coded Aperture, Levin, Fergus, Durand, Freeman 
Sparse Deconvolution
4D Frequency Analysis of Computational Cameras for Depth of Field Extension, Levin, Hasinoff, Green, Durand, and Freeman. SIGGRAPH 2009. Web Page
Motion-Invariant Photography, Levin, Sand, Cho, Durand, Freeman. SIGGRAPH 2008. Web Page
Noise Estimation from a Single Image, Liu, Freeman, Szeliski, and Kang
Image Magnification Using Level-Set Reconstruction, Morse and Schwartzwald
Bayesian Image Super-Resolution, Continued, Pickup, Capely, Roberts, and Zisserman
Fast Image/Video Upsampling, Shan, Li, Jia, and Tang. Web Page
High-quality Motion Deblurring from a Single Image, Shan, Jia, and Argarwala. Web Page
Image Super-resolution using Gradient Profile Prior, Sun, Sun, Xu, and Shum.
Deblurring Using Regularized Locally-Adaptive Kernel Regression, Takeda, Farsiu, and Milanfar. Web Page
Kernel Regression for Image Processing and Reconstruction, Takeda, Farsiu, Milanfar. Web Page
Exploiting the Sparse Derivative Prior for Super-Resolution and Image Demosaicing, Tappen, Russell, and Freeman
Bayesian Image Super-Resolution, Tipping and Bishop
Non-uniform Deblurring for Shaken Images, Whyte, Sivic, Zisserman, and Ponce. CVPR 2010
Deblurring Shaken and Partially Saturated Images, Whyte, Sivic, and Zisserman. ICCP 2012
Image Super-Resolution via Sparse Representation, Yang, Wright, Huang, and Ma 
Image Super-resolution as Sparse Representation of Raw Image Patches Code
Image Deblurring with Blurred/Noisy Image Pairs, Yuan, Sun, Quan, and Shum
Progressive Inter-scale and intra-scale Non-blind Image Deconvolution, Yuan, Sun, Quan, and Shum
Denoising vs. Deblurring: HDR Imaging Techniques Using Moving Cameras, Zhang, Deshpande, and Chen. CVPR 2010. Web Page
Robust Flash Deblurring, Zhuo and Sim. CVPR 2010. Web Page


Matting and Editing(抠图和图像编辑)

Interactive Digital Photomontage, Agarwala, Dontcheva, Agrawala, Drucker, Colburn, Curless, Salesin, and Cohen
Video SnapCut: Robust Video Object Cutout Using Localized Classifiers, Bai, Wang, Simons, and Saprio. SIGGRAPH 2009. Web Page
PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing, Barnes, Shechtman, Finkelstein, and Goldman. SIGGRAPH 2009. Web Page
Face Swapping: Automatically Replacing Faces in Photographs, Bitouk, Kumar, Dhillon, Belhumeur, and Nayar. SIGGRAPH 2008. Web Page
The Patch Transform and Its Applications to Image Editing, Cho, Butman, Avidan, and Freeman. Web Page
A Bayesian Approach to Digital Matting, Chuang, Curless, Salesin, and Szeliski
Geodesic Image and Video Editing, Criminisi, Sharp, Rother, and Perez. SIGGRAPH 2011.
Coordinates for Instant Image Cloning, Farbman, Hoffer, Lipman, Cohen-Or, and Lischinski. SIGGRAPH 2009. Web Page
Shared Sampling for Real-Time Alpha Matting, Gastal and Oliveira. Eurographics 2010. Web Page
Geodesic Star Convexity for Interactive Image Segmentation, Gulshan, Rother, Criminisi, Blake, and Zisserman. CVPR 2010. Web Page and Code
A Global Sampling Method for Alpha Matting, He, Rhemann, Rother, Tang, Sun. CVPR 2011.
Guided Image Filtering, He, Sun, Tang. ECCV 2011. Code
Light Mixture Estimation for Spatially Varying White Balance, Hsu, Mertens, Paris, Avidan, and Durand. Web Page
Arcimboldo-like Collage Using Internet Images, Huang, Zhang, and Zhang. Web Page
Drag-and-Drop Pasting, Jia, Sun, Tang, and Shum. Web Page
Exploring Photobios, Kemelmacher-Shlizerman, Shechtman, Garg, Seitz. SIGGRAPH 2011. Web Page
Seamless Image Stitching in the Gradient Domain, Levin, Zomet, Peleg, and WeissPhoto Clip Art, Lalonde, Hoiem, Efros, Rother, Winn, and Criminisi
A Closed Form Solution to Natural Image Matting, Levin, Lischinski, and Weiss Code
Spectral Matting, Levin, Rav-Acha, and Lischinski
Paint Selection, Liu, Sun, and Shum. SIGGRAPH 2009.
Poisson Image Editing, Perez, Gangnet, and Blake
A Perceptually Motivated Online Benchmark for Image Matting, Rhemann, Rother, Wang, Gelautz, Kohli, and Rott. Web Page
A Spatially Varying PSF-based Prior for Alpha Matting, Rhemann, Rother, Kohli, and Gelautz. CVPR 2010.
AutoCollage, Rother, Bordeaux, Hamadi, and Blake
Alpha Estimation in Natural Images, Ruzon and Tomasi
New Appearance Models for Natural Image Matting, Singaraju, Rother, and Rhemann
Interactive Editing of Massive Imagery Made Simple: Turning Atlanta into Atlantis, Summa, Scorzelli, Jiang, Bremer, and Pascucci. SIGGRAPH 2011. Web Page
Flash Matting, Sun, Li, Kang, and Shum
Fast Poisson Blending Using Multi-splines, Szeliski, Uyttendaele, and Steedly. ICCP 2011.
Soft Scissors : An Interactive Tool for Realtime High Quality Matting, Wang, Agrawala, and Cohen
Image and Video Matting: A Survey, Wang and Cohen

Warping and Morphing(图像扭曲和变形)

As-Rigid-As-Possible Shape Interpolation, Alexa, Cohen-Or, and Levin
Feature-Based Image Metamorphosis, Beier and Neely
Optimizing Content-Preserving Projections for Wide-Angle Images, Carroll, Agrawala, and Agarwala. SIGGRAPH 2009. Web Page
Detail Preserving Shape Deformation in Image Editing, Fang and Hart
Feature-Aware Texturing, Gal, Sorkine, and Cohen-Or
As-Rigid-As-Possible Shape Manipulation, Igarashi, Moscovich, and Hughes
Polymorph: Morphing Among Multiple Images , Lee, Wolberg, and Shin
Content-Preserving Warps for 3D Video Stabilization, Liu, Gleicher, Jin and Agarwala. SIGGRAPH 2009. Web Page
Moving Gradients: A Path-Based Method for Plausible Image Interpolation, Mahajan, Huang, Matusik, Ramamoorthi, and Belhumeur. SIGGRAPH 2009
Multi-operator Media Retargeting, Rubinstein, Shamir, and Avidan. SIGGRAPH 2009. Web Page
Regenerative Morphing, Shechtman, Rav-Acha, Irani, and Seitz. CVPR 2010. Web Page
Image Morphing: A Survey , Wolberg

Useful Techniques(其他相关技术)

Gaussian KD-Trees for Fast High-Dimensional Filtering, Adams, Gelfand, Dolson, and Levoy. SIGGRAPH 2009. Web Page
Fast High-Dimensional Filtering Using the Permutohedral Lattice, Adams, Baek, and Davis. Eurographics 2010. Web Page
Fast Approximate Energy Minimization via Graph Cuts, Boykov, Veksler, and Zabih
Edge-Avoiding Wavelets and thier Applications, Fattal Web Page
Graphical Models: Probabilistic Inference , Jordan and Weiss
Loopy Belief Propagation for Approximate Inference: An Empirical Study , Murphy, Weiss, and Jordan
Bilateral Filtering: Papers, Resources, Applications, Paris and Durand
Constant time O(1) bilateral filtering Porikli
Image Alignment and Stitching: A Tutorial, Szeliski
Bilateral Filtering for Gray and Color Images, Tomasi and Manduchi
Image Smoothing via L0 Gradient Minimization, Xu, Lu, Xu, and Jia. SIGGRAPH Asia 2011. Web Page
Real-Time O(1) Bilateral Filtering, Yang, Tan and Ahuja Source Code
SVM for Edge-Preserving Filtering, Yang, Wang and Ahuja

... and Beyond

Photographing long scenes with multi-viewpoint panoramas, Agarwala, Agrawala, Cohen, Salesin, and Szeliski
Video Face Replacement, Dale et al. SIGGRAPH ASIA 2011. Web Page
Convolution Pyramids, Farbman, Fattal, and Lischinski. SIGGRAPH ASIA 2011.
Candid Portrait Selection from Video, Fiss, Argarwala, and Curless. SIGGRAPH ASIA 2011. Web Page
Image-Based Rendering Using Image-Based Priors, Fitzgibbon, Wexler, and Zisserman
"GrabCut"--Interactive Foreground Extraction using Iterated Graph Cuts, Rother, Kolmogorov, and Blake Web Page
Photo Tourism: Exploring Photo Collections in 3D, Snavely, Seitz, and Szeliski Web Page

Books for General Reference

Digital Image Processing, Second Edition, Gonzalez and Woods
Computer Vision: A Modern Approach, Forsyth and Ponce
The Art and Science of Digital Compositing, Brinkmann
Multiple View Geometry in Computer Vision, Hartley and Zisserman
Linear Algebra and Its Applications, Strang
Computer Vision: Algorithms and Applications, Richard Szeliski
2018-05-09 10:19:08 Lucifer_Ji 阅读数 2903

ICCV图像处理相关论文总结(103篇)

1、Person ReID(行人再识别)(15)  

1Neural Person Search Machines

Hao Liu, Jiashi Feng,Zequn Jie, Karlekar Jayashree, Bo Zhao, Meibin Qi, Jianguo Jiang, Shuicheng Yan

 

2Cross-View Asymmetric Metric Learning for Unsupervised PersonRe-Identification

Hong-Xing Yu, Ancong Wu,Wei-Shi Zheng

 

3SHaPE: A Novel Graph Theoretic Algorithm for MakingConsensus-Based Decisions in Person Re-Identification Systems

Arko Barman, Shishir K.Shah

 

4A Two Stream Siamese Convolutional Neural Network for PersonRe-Identification

Dahjung Chung, KhalidTahboub, Edward J. Delp

 

5Efficient Online Local Metric Adaptation via Negative Samplesfor Person Re-Identification

Jiahuan Zhou, Pei Yu, WeiTang, Ying Wu

 

6Learning View-Invariant Features for Person Identification inTemporally Synchronized Videos Taken by Wearable Cameras

Kang Zheng, XiaochuanFan, Yuewei Lin, Hao Guo, Hongkai Yu, Dazhou Guo, Song Wang

 

7Deeply-Learned Part-Aligned Representations for PersonRe-Identification

Liming Zhao, Xi Li,Yueting Zhuang, Jingdong Wang

 

8Unlabeled Samples Generated by GAN Improve the PersonRe-Identification Baseline in Vitro

Zhedong Zheng, LiangZheng, Yi Yang

 

9Pose-Driven Deep Convolutional Model for PersonRe-Identification

Chi Su, Jianing Li,Shiliang Zhang, Junliang Xing, Wen Gao, Qi Tian

 

10Jointly Attentive Spatial-Temporal Pooling Networks forVideo-Based Person Re-Identification

Shuangjie Xu, Yu Cheng,Kang Gu, Yang Yang, Shiyu Chang, Pan Zhou

 

11RGB-Infrared Cross-Modality Person Re-Identification

Ancong Wu, Wei-Shi Zheng,Hong-Xing Yu, Shaogang Gong, Jianhuang Lai

 

12Multi-Scale Deep Learning Architectures for PersonRe-Identification

Xuelin Qian, Yanwei Fu,Yu-Gang Jiang, Tao Xiang, Xiangyang Xue

 

13Stepwise Metric Promotion forUnsupervised Video PersonRe-Identification

Zimo Liu;Dong Wang;Huchuan Lu

 

14Dynamic Label Graph Matching forUnsupervised VideoRe-Identification

Mang Ye; AndyJ. Ma; LiangZheng; Jiawei Li; Pong C. Yuen

 

15Jointly Attentive Spatial-TemporalPooling Networks forVideo-Based Person Re-Identification

Shuangjie Xu;Yu Cheng;Kang Gu; Yang Yang; Shiyu Chang; Pan Zhou

 

2、Pedestrian recognition(行人识别)(10)

1SBGAR: Semantics BasedGroup ActivityRecognition

XinLi, MooiChoo Chuah

 

2R-C3D: RegionConvolutional 3D Network for Temporal ActivityDetection

HuijuanXu, Abir Das, Kate Saenko

 

3Learning Long-TermDependenciesfor Action Recognition With a Biologically-Inspired Deep Network

YeminShi, YonghongTian, Yaowei Wang, Wei Zeng, Tiejun Huang

 

4Ensemble Deep Learningfor Skeleton-Based ActionRecognition Using Temporal Sliding LSTM Networks

InwoongLee, Doyoung Kim,Seoungyoon Kang, Sanghoon Lee

 

5Adaptive RNN Tree forLarge-Scale Human Action Recognition

WenboLi, Longyin Wen, Ming-Ching Chang,Ser Nam Lim, Siwei Lyu

 

6View Adaptive RecurrentNeural Networks for High Performance HumanAction Recognition From Skeleton Data

PengfeiZhang, Cuiling Lan, JunliangXing, Wenjun Zeng, Jianru Xue, Nanning Zheng

 

7Lattice Long Short-TermMemory for Human Action Recognition

LinSun, Kui Jia, Kevin Chen, Dit-YanYeung, Bertram E. Shi, Silvio Savarese

 

8Single Image ActionRecognition Using Semantic Body Part Actions

ZhichenZhao, Huimin Ma, Shaodi You

 

9RPAN: An End-To-EndRecurrent Pose-Attention Network for ActionRecognition in Videos

WenbinDu, Yali Wang, Yu Qiao

 

10Learning ActionRecognition Model From Depth and Skeleton Videos

HosseinRahmani, Mohammed Bennamoun

 

3、Pedestrian Retrieval(行人检索)(3)

1、SVDNet forPedestrian Retrieval

Yifan Sun;Liang Zheng; Weijian Deng;Shengjin Wang

 

2、HydraPlus-Net:Attentive Deep Featuresfor Pedestrian Analysis

Xihui Liu;Haiyu Zhao; Maoqing Tian; LuSheng; Jing Shao; Shuai Yi; Junjie Yan; XiaogangWang

 

3、Spatio-TemporalPerson Retrieval viaNatural Language Queries

Masataka Yamaguchi;Kuniaki Saito; YoshitakaUshiku; Tatsuya Harada

 

4、Tracking(跟踪)(16)

1Non-Markovian GloballyConsistent Multi-Object Tracking

AndriiMaksai, Xinchao Wang, Francois Fleuret, Pascal Fua

 

2CDTS: CollaborativeDetection, Tracking, and Segmentation for Online Multiple Object Segmentationin Videos

YeongJun Koh, Chang-Su Kim

 

3Online Multi-ObjectTracking Using CNN-Based Single Object Tracker With Spatial-Temporal AttentionMechanism

QiChu, Wanli Ouyang, Hongsheng Li, Xiaogang Wang, Bin Liu, Nenghai Yu

 

4Tracking theUntrackable: Learning to Track Multiple Cues With Long-Term Dependencies

AmirSadeghian, Alexandre Alahi, Silvio Savarese

 

5Learning Dynamic Siamese Networkfor Visual Object Tracking

QingGuo, Wei Feng, Ce Zhou, Rui Huang, Liang Wan, Song Wang

 

6CREST: ConvolutionalResidual Learningfor Visual Tracking

YibingSong,Chao Ma, Lijun Gong, Jiawei Zhang, Rynson W. H. Lau, Ming-Hsuan Yang

 

7LearningBackground-Aware CorrelationFilters for Visual Tracking

HamedKianiGaloogahi, Ashton Fagg, Simon Lucey

 

8Need for Speed: ABenchmark for HigherFrame Rate Object Tracking

HamedKianiGaloogahi, Ashton Fagg, Chen Huang, Deva Ramanan, Simon Lucey

 

9Parallel Tracking andVerifying: AFramework for Real-Time and High Accuracy Visual Tracking

HengFan,Haibin Ling

 

10Non-Rigid ObjectTracking viaDeformable Patches Using Shape-Preserved KCF and Level Sets

XinSun,Ngai-Man Cheung, Hongxun Yao, Yiluan Guo

 

11Tracking as OnlineDecision-Making:Learning a Policy From Streaming Videos With ReinforcementLearning

JamesSupancic,III,Deva Ramanan

 

12Learning Policies forAdaptive TrackingWith Deep Feature Cascades

ChenHuang,Simon Lucey, Deva Ramanan

 

13Robust Object TrackingBased onTemporal and Spatial Deep Networks

ZhuTeng,Junliang Xing, Qiang Wang, Congyan Lang, Songhe Feng, Yi Jin

 

14Non-Markovian GloballyConsistentMulti-Object Tracking

AndriiMaksai,Xinchao Wang, Francois Fleuret, Pascal Fua

 

15Beyond StandardBenchmarks:Parameterizing Performance Evaluation in Visual Object Tracking

LukaCehovinZajc, Alan Lukezic, Ales Leonardis, Matej Kristan

 

16Online Multi-ObjectTracking UsingCNN-Based Single Object Tracker With Spatial-Temporal AttentionMechanism

QiChu, WanliOuyang, Hongsheng Li, Xiaogang Wang, Bin Liu, Nenghai Yu

 

5、Object Detection(目标检测)(13)

1、Amulet: AggregatingMulti-LevelConvolutional Features for Salient Object Detection

PingpingZhang, Dong Wang, Huchuan Lu,Hongyu Wang, Xiang Ruan

 

2、Flow-Guided FeatureAggregation forVideo Object Detection

Xizhou Zhu,Yujie Wang, Jifeng Dai, Lu Yuan,Yichen Wei

 

3、DeNet: ScalableReal-Time ObjectDetection With Directed Sparse Sampling

LachlanTychsen-Smith, Lars Petersson

 

4、Recurrent ScaleApproximation forObject Detection in CNN

Yu Liu,Hongyang Li, Junjie Yan, FangyinWei, Xiaogang Wang, Xiaoou Tang

 

5、Adversarial Examplesfor SemanticSegmentation and Object Detection

Cihang Xie,Jianyu Wang, Zhishuai Zhang,Yuyin Zhou, Lingxi Xie, Alan Yuille

 

6、Temporal DynamicGraph LSTM forAction-Driven Video Object Detection

Yuan Yuan,Xiaodan Liang, Xiaolong Wang,Dit-Yan Yeung, Abhinav Gupta

 

7、Chained CascadeNetwork for ObjectDetection

Wanli Ouyang,Kun Wang, Xin Zhu, XiaogangWang

 

8、Online Video ObjectDetection UsingAssociation LSTM

Yongyi Lu,Cewu Lu, Chi-Keung Tang

 

9、Focal Loss for DenseObject Detection

Tsung-Yi Lin,Priya Goyal, Ross Girshick,Kaiming He, Piotr Dollar

 

10、Spatial Memory forContext Reasoning inObject Detection

Xinlei Chen,Abhinav Gupta

 

11、2D-Driven 3D ObjectDetection in RGB-DImages

Jean Lahoud,Bernard Ghanem

 

12、Moving ObjectDetection in Time-Lapseor Motion Trigger Image Sequences Using Low-Rank andInvariant SparseDecomposition

MoeinShakeri, Hong Zhang

 

13、Soft-NMS --Improving Object DetectionWith One Line of Code

NavaneethBodla, Bharat Singh, RamaChellappa, Larry S. Davis

 

6、Pose estimation(姿态估计)(15)

1Real-TimeMonocular Pose Estimation of 3D Objects Using Temporally Consistent Local ColorHistograms

Henning Tjaden, Ulrich Schwanecke, Elmar Schomer

 

2Benchmarkingand Error Diagnosis in Multi-Instance Pose Estimation

Matteo Ruggero Ronchi, Pietro Perona

 

3Towards3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach

Xingyi Zhou, Qixing Huang, Xiao Sun, Xiangyang Xue, YichenWei

 

4AdversarialPoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation

Yu Chen, Chunhua Shen, Xiu-Shen Wei, Lingqiao Liu, JianYang

 

5LearningFeature Pyramids for Human Pose Estimation

Wei Yang, Shuang Li, Wanli Ouyang, Hongsheng Li, XiaogangWang

 

6MakingMinimal Solvers for Absolute Pose Estimation Compact and Robust

Viktor Larsson, Zuzana Kukelova, Yinqiang Zheng

 

7RMPE:Regional Multi-Person Pose Estimation

Hao-Shu Fang, Shuqin Xie, Yu-Wing Tai, Cewu Lu

 

8ASimple yet Effective Baseline for 3D Human Pose Estimation

Julieta Martinez, Rayat Hossain, Javier Romero, James J.Little

 

9RobustHand Pose Estimation During the Interaction With an Unknown Object

Chiho Choi, Sang Ho Yoon, Chin-Ning Chen, Karthik Ramani

 

10Monocular3D Human Pose Estimation by Predicting Depth on Joints

Bruce Xiaohan Nie, Ping Wei, Song-Chun Zhu

 

11DeepGlobally Constrained MRFs for Human Pose Estimation

Ioannis Marras, Petar Palasek, Ioannis Patras

 

12BinarizedConvolutional Landmark Localizers for Human Pose Estimation and Face AlignmentWith Limited Resources

Adrian Bulat, Georgios Tzimiropoulos

 

13Learningto Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation

Bugra Tekin, Pablo Marquez-Neila, Mathieu Salzmann, PascalFua

 

14ActiveLearning for Human Pose Estimation

Buyu Liu, Vittorio Ferrari

 

15Human Pose Estimation Using Global and LocalNormalization

Ke Sun, Cuiling Lan, Junliang Xing, Wenjun Zeng, Dong Liu,Jingdong Wang

 

7、Semantic Segmentation(语义分割)(12)

1Predicting DeeperInto the Future of Semantic Segmentation   

Pauline Luc, NataliaNeverova, Camille Couprie, Jakob Verbeek, Yann LeCun

 

2Cascaded Feature Network for SemanticSegmentation of RGB-D Images

Di Lin, GuangyongChen, Daniel Cohen-Or, Pheng-Ann Heng, Hui Huang

 

3Video Deblurring via Semantic Segmentation andPixel-Wise Non-Linear Kernel

Wenqi Ren, JinshanPan, Xiaochun Cao, Ming-Hsuan Yang

 

4Adversarial Examples for Semantic Segmentationand Object Detection

Cihang Xie, JianyuWang, Zhishuai Zhang, Yuyin Zhou, Lingxi Xie, Alan Yuille

 

5VQS: Linking Segmentations to Questions andAnswers for Supervised Attention in VQA and Question-Focused SemanticSegmentation

Chuang Gan, YandongLi, Haoxiang Li, Chen Sun, Boqing Gong

 

6Curriculum Domain Adaptation for SemanticSegmentation of Urban Scenes

Yang Zhang, PhilipDavid, Boqing Gong

 

7Bringing Background Into the Foreground:Making All Classes Equal in Weakly-Supervised Video Semantic Segmentation

Fatemeh Sadat Saleh,Mohammad Sadegh Aliakbarian, Mathieu Salzmann, Lars Petersson, Jose M. Alvarez

 

8RDFNet: RGB-D Multi-Level Residual FeatureFusion for Indoor Semantic Segmentation

Seong-Jin Park,Ki-Sang Hong, Seungyong Lee

 

93D Graph Neural Networks for RGBD SemanticSegmentation

Xiaojuan Qi, RenjieLiao, Jiaya Jia, Sanja Fidler, Raquel Urtasun

 

10Semi Supervised Semantic Segmentation UsingGenerative Adversarial Network

Nasim Souly, ConcettoSpampinato, Mubarak Shah

 

11Deep Dual Learning for SemanticImageSegmentation

Ping Luo, GuangrunWang, LiangLin, Xiaogang Wang

 

12Universal Adversarial PerturbationsAgainstSemantic Image Segmentation

Jan Hendrik Metzen,MummadiChaithanya Kumar, Thomas Brox, Volker Fischer

 

8、Instance Segmentation(实例分割)(2)

1SGN: Sequential Grouping Networks for InstanceSegmentation

Shu Liu, Jiaya Jia,Sanja Fidler, Raquel Urtasun

 

2Mask R-CNN

Kaiming He, GeorgiaGkioxari, Piotr Dollar, Ross Girshick

 

9、Crowd counting(人群计数)(2)

1Generating High-Quality Crowd Density MapsUsing Contextual Pyramid CNNs

Vishwanath A.Sindagi, Vishal M. Patel

 

2Spatiotemporal Modeling for Crowd Counting inVideos

Feng Xiong, XingjianShi, Dit-Yan Yeung

 

10、Vehicle ReID(车辆识别)(2)

1Learning Deep Neural Networksfor Vehicle Re-ID With Visual-Spatio-Temporal Path Proposals

Yantao Shen, Tong Xiao, Hongsheng Li, Shuai Yi, Xiaogang Wang

 

2Orientation Invariant FeatureEmbedding and Spatial Temporal Regularization for Vehicle Re-Identification

Zhongdao Wang, Luming Tang, Xihui Liu, Zhuliang Yao, Shuai Yi, JingShao, Junjie Yan, Shengjin Wang, Hongsheng Li, Xiaogang Wang

 

11、GAN(生成对抗网络)(11)

1Unlabeled SamplesGenerated by GAN Improve the Person Re-Identification Baseline in Vitro

ZhedongZheng, Liang Zheng, Yi Yang

 

2Xudong Mao, Qing Li,Haoran Xie, Raymond Y.K. Lau, Zhen Wang, Stephen Paul Smolley

 

3StackGAN: Text toPhoto-Realistic Image Synthesis With Stacked Generative Adversarial Networks

HanZhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang,Dimitris N. Metaxas

 

4Semantic Image Synthesisvia Adversarial Learning

HaoDong, Simiao Yu, Chao Wu, Yike Guo

 

5Dual Motion GAN forFuture-Flow Embedded Video Prediction

XiaodanLiang, Lisa Lee, Wei Dai, Eric P. Xing

 

6GANs for Biological ImageSynthesis

AntonOsokin, Anatole Chessel, Rafael E. Carazo Salas, Federico Vaggi

 

7Beyond Face Rotation:Global and Local Perception GAN for Photorealistic and Identity PreservingFrontal View Synthesis

RuiHuang, Shu Zhang, Tianyu Li, Ran He

 

8CVAE-GAN: Fine-GrainedImage Generation Through Asymmetric Training

JianminBao, Dong Chen, Fang Wen, Houqiang Li, Gang Hua

 

9DualGAN: UnsupervisedDual Learning for Image-To-Image Translation

ZiliYi, Hao Zhang, Ping Tan, Minglun Gong

 

10Recurrent Topic-TransitionGAN for Visual Paragraph Generation

XiaodanLiang, Zhiting Hu, Hao Zhang, Chuang Gan, Eric P. Xing

 

11Realistic Dynamic Facial Textures From a Single ImageUsing GANs

KyleOlszewski, Zimo Li, Chao Yang, Yi Zhou, Ronald Yu, Zeng Huang, Sitao Xiang,Shunsuke Saito, Pushmeet Kohli, Hao Li

 

12、video summarization(视频摘要)(2)

1Weakly SupervisedSummarization of Web Videos

RameswarPanda, Abir Das, Ziyan Wu, Jan Ernst, Amit K. Roy-Chowdhury

 

2Summarization andClassification of Wearable Camera Streams by Learning the Distributions OverDeep Features of Out-Of-Sample Image Sequences

AlessandroPerina, Sadegh Mohammadi, Nebojsa Jojic, Vittorio Murino

 

2016-11-18 10:55:57 yangleo1987 阅读数 23423

所谓数字图像处理,是指将图像信号转换成数字信号并利用计算机对其进行处理的过程。20 世纪 50 年代,电子计算机已经发展到一定水平,人们开始利用计算机来处理图形和图像信息,这便是早期的图像处理。早期图像处理的目的是改善图像的质量,它以人为对象,以改善人的视觉效果为目的。数字图像处理作为一门学科大约形成于 20 世纪 60 年代初期。图像处理中,一般输入的是质量低的图像,而输出的是改善质量后的图像,常用的图像处理方法有图像增强、复原、编码、压缩等。

下面维视图像为您简单介绍一下数字图像处理的常用技术方法:

图像编码压缩:图像编码压缩技术可减少描述图像的数据量(即比特数),以便节省图像传输、处理时间和减少所占用的存储器容量。压缩可以在不失真的前提下获得,也可以在允许的失真条件下进行。编码是压缩技术中最重要的方法,它在图像处理技术中是发展最早且比较成熟的技术。

图像变换:由于图像阵列很大,直接在空间域中进行处理,涉及计算量很大。因此,往往采用各种图像变换的方法,如傅立叶变换、沃尔什变换、离散余弦变换等间接处理技术,将空间域的处理转换为变换域处理。这样不仅可减少计算量,而且可获得更有效的处理(如傅立叶变换可在频域中进行数字滤波处理)。小波变换这种方式在时域和频域中都具有良好的局部化特性,它在图像处理中也有着广泛而有效的应用。

图像描述:图像描述是图像识别和理解的必要前提。作为最简单的二值图像可采用其几何特性描述物体的特性,一般图像的描述方法采用二维形状描述,它有边界描述和区域描述两类方法。对于特殊的纹理图像可采用二维纹理特征描述。随着图像处理研究的深入发展,已经开始进行三维物体描述的研究,提出了体积描述、表面描述、广义圆柱体描述等方法。

图像分割:图像分割是数字图像处理中的关键技术之一。图像分割是将图像中有意义的特征部分提取出来,其有意义的特征如图像中的边缘、区域等,这是进一步进行图像识别、分析和理解的基础。虽然目前已研究出不少边缘提取、区域分割的方法,但还没有一种普遍适用于各种图像的有效方法。因此,对图像分割的研究还在不断深入之中,是目前图像处理中研究的热点之一。

图像增强和复原:图像增强和复原的目的是为了提高图像的质量,如去除噪声,提高图像的清晰度等。图像增强不考虑图像降质的原因,突出图像中所感兴趣的部分。如强化图像高频分量,可使图像中物体轮廓清晰,细节明显;如强化低频分量可减少图像中噪声影响。图像复原要求对图像降质的原因有一定的了解,一般应根据降质过程建立“降质模型”,再采用某种滤波方法,恢复或重建原来的图像。

图像分类(识别):图像分类(识别)属于模式识别的范畴,其主要内容是图像经过某些预处理(增强、复原、压缩)后,进行图像分割和特征提取,从而进行判决分类。图像分类常采用经典的模式识别方法,有统计模式分类和句法(结构)模式分类,近年来新发展起来的模糊模式识别和人工神经网络模式分类在图像识别中也越来越受到重视。

接下来,维视图像再为大家讲讲图像的基本属性有哪些:

图像的亮度:也称为灰度,它是颜色的明暗变化,常用 0 %~ 100 % ( 由黑到白 ) 表示。以下三幅图是不同亮度对比。

 

图像的对比度:即画面黑与白的比值,也就是从黑到白的渐变层次。比值越大,从黑到白的渐变层次就越多,从而色彩表现越丰富。以下两幅图是不同对比度下的画面对比。

 

直方图:表示图像中具有每种灰度级的象素的个数,反映图像中每种灰度出现的频率。图像在计算机中的存储形式,就像是有很多点组成一个矩阵,这些点按照行列整齐排列,每个点上的值就是图像的灰度值,直方图就是每种灰度在这个点矩阵中出现的次数。下图就是一幅图片的灰度直方图:

 

图像的噪声:就像对于听觉而言,在打电话时对方说话我们有时候会听到很嘈杂的噪声,以至于听不清楚对方在说什么。同样的,对于图像,原本我们可以很清晰的看到一幅图像,但是有时候图像上会有一些我们不需要的图案,使我们无法很清楚的看清一幅图,这就是图像的噪声。

除了以上我们介绍过的几种常用的数字图像处理技术方法外,一般还有:

直方图均衡化:通过灰度变换将一幅图像转换为另一幅具有均衡直方图的图像,即在一定灰度范围内具有相同的象素点数的图像的过程。

图像的加减运算:两幅图像的加减运算,就是将图像对应的存储矩形点列上的灰度值进行加减运算。图像相加可以将一幅图像的内容加到另一幅图像上,可以实现二次曝光,也可一对同一个场景的多幅图像求平均值,这样可以降低噪声。图像相减可以用于运动检测或去除图像中不需要的加性图案。

常用的去噪方法:主要是采用滤波器对带噪声图像进行滤波处理,如算术平均滤波、中值滤波等。

随着计算机技术的发展,数字图像处理技术已经深入到我们生活中的方方面面,其中,在娱乐休闲上的应用更是深入人心,如电影特效制作、电脑电子游戏、数码相机、视频播放、数字电视等。维视图像公司研发的XAVIS软件平台和SVS工业智能相机系统等,均包含了丰富的数字图像处理技术和方法,可轻松完成各种数字图像处理任务,为客户的图像处理结果提供专业而可靠的保障。

2016-04-15 13:36:30 j_study 阅读数 2079

计算机视觉、图像处理方面的论文阅读笔记,

推荐大家看一下http://zhangliliang.com/,作者:在路上

方便吐舌头懒人偷笑了解计算机视觉,图像处理方面的进展。

感谢作者的无私贡献。