丕子 » SIGGRAPH

SIGGRAPH2011和IJCAI2011关于CV的Paper

丕子 — Sat, 23 Apr 2011 04:32:58 +0000

- A selection of computer vision related papers -
See IJCAI 2011 page for a non selective list.

Accommodating Human Variability in Human-Robot Teams through Theory of Mind: Laura Hiatt, Anthony Harrison, Greg Trafton
Aesthetic Guidelines Driven Photography By Robots: Raghudeep Gadde, Kamalakar Karlapalem
Capturing an Evader in a Polygonal Environment with Obstacles: Deepak Bhadauria, Volkan Isler
Conics With A Common Axis of Symmetry: Properties and Applications to Camera Calibration: Zijian Zhao
Exploiting Probabilistic Knowledge under Uncertain Sensing for Efficient Robot Behaviour: Marc Hanheide, Nick Hawes, Charles Gretton, Alper Aydemir, Hendrik Zender, Andrzej Pronobis, Jeremy Wyatt, Moritz Göbelbecker
Robotic Object Detection: Learning to Improve the Classifiers using Sparse Graphs for Path Planning: Zhaoyin Jia, Ashutosh Saxena, Tsuhan Chen
User-dependent Aspect Model for Collaborative Activity Recognition: Wenchen Zheng, Qiang Yang

============

- A selection of computer vision related papers - Papers conditionally accepted
See Ke-Sen Huang's SIGGRAPH 2011 page for a non selective list.

Nonlinear Revision Control for Images (project, abstract): Hsiang-Ting Chen (National Tsing Hua University, Taiwan), Li-Yi Wei (Microsoft Research), Chun-Fa Chang (National Taiwan Normal University, Taiwan)
Example-based Image Color and Tone Style Enhancement: Baoyuan Wang (Zhejiang University), Yizhou Yu (University of Illinois at Urbana-Champaign and Zhejiang University), Ying-Qing Xu (Microsoft Research Asia)
Perceptually Based Tone Mapping for Low-Light Conditions: Adam G. Kirk, James F. O'Brien (University of California, Berkeley)
Depixelizing Pixel Art: Johannes Kopf (Microsoft Research), Dani Lischinski (The Hebrew University of Jerusalem)
Switchable Primaries Using Shiftable Layers of Color Filter Arrays: Behzad Sajadi, Aditi Majumder, Kazuhiro Hiwada, Atsuto Maki, Ramesh Raskar (MIT Media Lab)
Exploring Photobios: Ira Kemelmacher-Shlizerman, Rahul Garg, Steven M. Seitz (University of Washington), Eli Shechtman (Adobe Systems, Inc.)
Laplacian Filters: Edge-aware Image Processing with a Laplacian Pyramid: Sylvain Paris, Samuel W. Hasinoff (Toyota Technological Institute at Chicago), Jan Kautz (University College London)
Video-based Characters - Creating New Human Performances from a Multi-view Video Database: Feng Xu (Tsinghua University, Beijing), Yebin Liu, Carsten Stoll (Max-Planck-Institut Informatik), James Tompkin (University College London), Gaurav Bharaj (Max-Planck-Institut Informatik), Qionghai Dai (Tsinghua University, Beijing), Hans-Peter Seidel (Max-Planck-Institut Informatik), Jan Kautz (University College London), Christian Theobalt (Max-Planck-Institut Informatik)

===========

- A selection of computer vision papers -
See Ke-Sen Huang's Eurographics 2011 page for a non selective list.

State-of-the-Art Reports

State of the Art in Computational Plemoptic Imaging (PDF, project): Gordon Wetzstein, Ivo Ihrke, Douglas Lanman, Wolfgang Heidrich

Session: Quality and Scalability

Freehand HDR imaging of moving scenes with simultaneous resolution enhancement (PDF, project, results): Henning Zimmer, Andres Bruhn, Joachim Weickert

Session: Non-Photorealistic Rendering

Estimating Color and Texture Parameters for Vector Graphics (PDF, supplementary material, video): Stefan Jeschke, David Cline, Peter Wonka

Session: Image and Video

Blur-Aware Image Downsizing (PDF, project, video, results, supplementary material): Matthew Trentacoste, Rafal Mantiuk, Wolfgang Heidrich
Image Retargeting Quality Assessment (PDF, abstract): Yong-Jin Liu, Xi Luo, Yu-Ming Xuan, Wen-Feng Chen, Xiao-Lan Fu
Image and Video Abstraction by Coherence-Enhancing Filtering (PDF, project, results, videos): Jan Eric Kyprianidis, Henry Kang

注：以上内容选择CVPapers

GRAPH：想改变现实么？

丕子 — Fri, 15 Oct 2010 09:54:16 +0000

Photoshop CS5的内容感知填充能清除和自动填充静止照片中的物体，现在德国伊尔梅瑙科技大学研究人员开发出一种软件，能几乎实时的删除视频中选定的物体。它使用的技术与内容感知填充并不相同，清除视频中任意物体的效果是利用略有失真的图像合成实现的，软件首先降低图像质量，移除物体，然后增加图像质量，这一切都在40毫秒时间内发生，因此肉眼感觉不到图像的变化。研究人员还计划在未来开发出一款Android版本。

Youtube上有演示视频，我看了下，真的很有用。实在不行翻墙看看。

SIGGRAPH 2010: 微软的模糊照片自动处理

丕子 — Sun, 01 Aug 2010 23:24:44 +0000

在2010年度的SIGGRAPH图形会议上，微软研究院的研究人员，介绍了一篇文章《Image Deblurring using Inertial Measurement Sensors》（pdf），演示了利用照相机或手机自带的“惯性测量传感器”实现图像自动去模糊。研究人员开发出一种去模糊算法，利用陀螺仪和加速计，从照相机在曝光过程中的加速度和角速度估算出一个模糊函数，使用最优方法推断出潜在的图形。这种方法可以自动的对每个像素进行处理。

相关链接：论文pdf, 幻灯片，高清大图

SIGGRAPH 2010--虚拟的虫子

丕子 — Sun, 01 Aug 2010 05:34:55 +0000

Squidsoup's Glowing Pathfinder Bugs：SIGGRAPH 2010为观众展示了最好的电脑动画和视觉特效，由Anthony Rowe在Squidsoup数字艺术集团协助下完成这套动画交互系统在沙坑中投射出的虫子影像并不是简单个一个动画影像，从下面的视频上我们看出，观众甚至可以参与互动，从沙坑中将虫子捞至手中。

不难想象，如若此项技术逐渐成熟，也许这种动画投影交互技术将是未来人机交互甚至虚拟宠物的基础，届时也许采用这种技术的的电子宠物可能就像曾经流行的宠物小鸡一样普及了。

SIGGRAPH'10的一篇论文--NETRA:视力自动评测和矫正

丕子 — Mon, 05 Jul 2010 23:00:58 +0000

MIT媒体实验室的研究人员开发出一款智能手机应用软件，让用户能衡量自己眼睛的屈光不正（如近视、远视和散光），并提供矫正屈光不正的方法。

用户从一个售价2美元的光学适配器注视智能手机的屏幕，应用程序会在上面展示发光的条纹，通过调整显示器直至条纹对齐。然后用户需要在不同地点和不同方位重复进行上述操作。这款应用程序在不同清晰度的智能手机上有不同的效果。以Nexus One手机为例，它能帮助判断出0.4屈光度以内的屈光不正，而清晰度更高的iPhone 4手机，则能提高至0.28屈光度以内。在缺乏有经验的眼科医生和诊断设备的发展中国家，这种廉价的诊断屈光不正的方法将能得到广泛应用。

这里有视频（Mov）。详细的论文资料：

NETRA: Interactive Display for Estimating

Refractive Errors and Focal Range

Vitor F. Pamplona* Ankit Mohan Manuel M. Oliveira* Ramesh Raskar
Camera Culture Group - MIT Media Lab
* Visiting from Instituto de Informática - UFRGS

To appear at ACM SIGGRAPH 2010

SIGGRAPH'10 Paper Frequently Asked Questions More Info

Ilustration: Tiago Allen

Figure 1: Can a person look at a portable display, click on a few buttons and recover his refractive condition? Our optometry solution combines inexpensive optical elements and interactive software components to create a new portable and inexpensive optometry device.

Abstract

We introduce an interactive, portable, and inexpensive solution for estimating refractive errors in the human eye. While expensive optical devices for automatic estimation of refractive correction exist, our goal is to greatly simplify the mechanism by putting the human subject in the loop. Our solution is based on a high-resolution programmable display and combines inexpensive optical elements, interactive GUI, and computational reconstruction. The key idea is to interface a lenticular view-dependent display with the human eye at close range - a few millimeters apart. Via this platform, we create a new range of interactivity that is extremely sensitive to parameters of the human eye, such as the refractive errors, focal range, focusing speed, lens opacity, etc. We propose several simple optical setups, verify their accuracy, precision, and validate them in a user study.

Please look at FAQ for contact information, collaboration opportunities and clinical study plans.

Paper

High Resolution (7MB)
Low Resolution (600K)

Citation: Vitor F. Pamplona, Ankit Mohan, Manuel M. Oliveira, Ramesh Raskar. NETRA: Interactive Display for Estimating Refractive Errors and Focal Range. Proc. of SIGGRAPH 2010 (ACM Transactions on Graphics 29, 4), 2010.

Bibtex:

@article{Pamplona_et_al_2010,
  author = {Vitor F. Pamplona and Ankit Mohan and Manuel M. Oliveira and Ramesh Raskar},
  title = {NETRA: Interactive Display for Estimating Refractive Errors and Focal Range },
  journal = {ACM Transactions on Graphics (proceedings of ACM SIGGRAPH)},
  year = {2010},
  volume = {29},
  number = {4},
}

Videos

MIT Media Lab LabCast: Credit, Paula Aguilera and Jonathan Williams

Pictures

Group Picture

NETRA team: Ankit Mohan, Manuel M. Oliveira Neto, Vitor Pamplona and Ramesh Raskar at the MIT Media Lab.
Photo: Jonathan Williams

Individual Pictures

Vitor Pamplona demonstrates NETRA	Vitor Pamplona demonstrates NETRA
Manuel M. Oliveira demonstrates NETRA	Manuel and Vitor
Ramesh Raskar demonstrates NETRA	Ramesh and Ankit
Ankit Mohan demonstrates NETRA	Ankit Mohan demonstrates NETRA

IDEAS Competition

Vitor Pamplona, Margaret McKenna, Ankit Mohan and Chika Ekeji. Photo by Xun (Helen) Hou	Vitor Pamplona, Margaret McKenna, Ankit Mohan and Chika Ekeji. Photo by Xun (Helen) Hou
Margaret McKenna, Chika Ekeji, Ankit Mohan and Vitor Pamplona. Photo by Xun (Helen) Hou	Photo by Xun (Helen) Hou

Prototypes in action

Photo: Michal Massey

User study and Experimental Validation

One of our team members visiting an Optometrist

Initial Exploration

SIGGRAPH 2010 papers &浙大周昆及学生的几篇论文

丕子 — Mon, 24 May 2010 06:35:10 +0000

图像学的牛会啊，论文早已经出来了，地址是 SIGGRAPH 2010 papers。国内牛人浙大周昆和他的学生中了4篇，真好。大家看看吧。

Siggraph and TOG papers

Qiming Hou, Hao Qin, Wenyao Li, Baining Guo and Kun Zhou, "Micropolygon Ray Tracing with Defocus and Motion Blur", ACM Trans. on Graphics (Siggraph), 2010.
Xin Sun, Kun Zhou, Stephen Lin and Baining Guo, "Line Space Gathering for Single Scattering in Large Scenes", ACM Trans. on Graphics (Siggraph), 2010.
Zhong Ren, Kun Zhou, Tengfei Li, Wei Hua and Baining Guo, "Interactive Hair Rendering Under Environment Lighting", ACM Trans. on Graphics (Siggraph), 2010.
Lvdi Wang, Kun Zhou, Yizhou Yu and Baining Guo, "Vector Solid Textures", ACM Trans. on Graphics (Siggraph), 2010.

Other journal papers

Qiming Hou, Xin Sun, Kun Zhou, Christian Lauterbach and Dinesh Manocha, "Memory-Scalable GPU Spatial Hierarchy Construction", IEEE Transactions on Visualization & Computer Graphics, 2010.
Kun Zhou, Minmin Gong, Xin Huang and Baining Guo, "Data-Parallel Octrees for Surface Reconstruction", IEEE Transactions on Visualization & Computer Graphics, 2010.
Kun Zhou, Weiwei Xu, Yiying Tong and Mathieu Desbrun, "Deformation Transfer to Multi-Component Objects", Computer Graphics Forum (Eurographics), 2010.
Xin Sun, Qiming Hou, Zhong Ren, Kun Zhou and Baining Guo, "Radiance Transfer Biclustering for Real-time All-frequency Bi-scale Rendering", IEEE Transactions on Visualization & Computer Graphics, 2010.

[Paper] 一篇SiGGRAPH09的文章：PatchMatch

丕子 — Fri, 26 Mar 2010 02:11:31 +0000

PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing
ACM Transactions on Graphics (Proc. SIGGRAPH), August 2009

Connelly Barnes, Eli Shechtman, Adam Finkelstein,
Dan B Goldman

Structural image editing. Left to right: (a) the original image; (b) a hole is marked (magenta) and we use line constraints (red/green/blue) to improve the continuity of the roofline; (c) the hole is filled in; (d) user-supplied line constraints for retargeting; (e) retargeting using constraints eliminates two columns automatically; and (f) user translates the roof upward using reshuffling.

Abstract

This paper presents interactive image editing tools using a new randomized algorithm for quickly finding approximate nearest neighbor matches between image patches. Previous research in graphics and vision has leveraged such nearest-neighbor searches to provide a variety of high-level digital image editing tools. However, the cost of computing a field of such matches for an entire image has eluded previous efforts to provide interactive performance. Our algorithm offers substantial performance improvements over the previous state of the art (20-100x), enabling its use in interactive editing tools. The key insights driving the algorithm are that some good patch matches can be found via random sampling, and that natural coherence in the imagery allows us to propagate such matches quickly to surrounding areas. We offer theoretical analysis of the convergence properties of the algorithm, as well as empirical and practical evidence for its high quality and performance. This one simple algorithm forms the basis for a variety of tools – image retargeting, completion and reshuffling – that can be used together in the context of a high-level image editing application. Finally, we propose additional intuitive constraints on the synthesis process that offer the user a level of control unavailable in previous methods.

Citation (BibTeX)

Connelly Barnes, Eli Shechtman, Adam Finkelstein, and Dan B Goldman. PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing. ACM Transactions on Graphics (Proc. SIGGRAPH). 28(3) August 2009.

Files
Paper (7 MB PDF)
Download Video (Long, 5 minutes) (46 MB MPEG-4)
Streaming Video (Short, 3 minutes)

Additional Links
Adobe Website

Photoshop CS5向用户展示了说服其升级的理由：Photoshop团队产品经理Bryan O’Neil-Hughes在演示视频中介绍了一个令人眼前一亮的新特性——内容感知填充。

利用这项功能，用户可以很容易消除图像中的镜头光斑；把原本有零零碎碎垃圾的地面变成完美的草坪；从画面中移除一棵大树，让Photoshop 自动的替换上草和天空，使整个画面浑然一体。

强大的PS工具将让人无法区分什么是真实，什么又被修改过了。演示视频发表在Youtube，这项神奇功能背后的算法来自普林斯顿大学的计算机科学家，他们在去年的SIGGRAPH上演示了该功能。

查看：论文（PDF），视频（MP4）

浙大周昆中４篇SIGGRAPH Asia 2009（被TOG收录）

丕子 — Fri, 09 Oct 2009 15:53:17 +0000

如，这个会议排在图形学第二，是SIGGRAPH 以外唯一被图形学最牛的杂志TOG收录的会议，去年总共接受了59篇论文，今年的情况暂时不知道。
另外周昆还中了3篇SIGGRAPH ，因此今年的TOG将会达到7篇。
而TOP一年也只有100多篇，这个实力在世界范围内也是顶尖高手。

１.Out-of-Core Detail-Preserving Mesh Deformation

Xiaohan Shi, Hujun Bao, Kun Zhou.

ACM TOG (SIGGRAPH Asia 2009), conditionally accepted
２.Motion Field Texture Synthesis

Chongyang Ma, Li-Yi Wei, Baining Guo, Kun Zhou.

ACM TOG (SIGGRAPH Asia 2009), conditionally accepted
３.RenderAnts: Interactive REYES Rendering on GPUs

Kun Zhou, Qiming Hou, Zhong Ren, Minmin Gong, Xin Sun, Baining Guo.

ACM TOG (SIGGRAPH Asia 2009), conditionally accepted, [Tech Report] [Video]
４.Debugging GPU Stream Programs Through Automatic Dataflow Recording and Visualization

Qiming Hou, Kun Zhou, Baining Guo.

ACM TOG (SIGGRAPH Asia 2009), conditionally accepted, [Tech Report]
http://www.kunzhou.net/

周昆最近几年的TOG数目：
09 7
08 6
07 4+1（在当年会议上做了一次关于网格划分的课程，是大陆学者第一次也是迄今为止唯一的一次）
06 4
05 3
04 1
03 1
。。。。。。。。
可以看到是越来越猛
他的个人主页，可以去看看他发的文章，这几年只在SIGGRAPH Asia 和SIGGRAPH 这两个会议上投论文，这才是真正意义上的顶尖。

Scene Completion Using Millions of Photographs

丕子 — Sat, 03 Oct 2009 15:16:45 +0000

来自：http://graphics.cs.cmu.edu/projects/scene-completion/

Scene Completion Using Millions of Photographs

People

Abstract

What can you do with a million images? In this paper we present a new image completion algorithm powered by a huge database of photographs gathered from the Web. The algorithm patches up holes in images by finding similar image regions in the database that are not only seamless but also semantically valid. Our chief insight is that while the space of images is effectively infinite, the space of semantically differentiable scenes is actually not that large. For many image completion tasks we are able to find similar scenes which contain image fragments that will convincingly complete the image. Our algorithm is entirely data-driven, requiring no annotations or labelling by the user. Unlike existing image completion methods, our algorithm can generate a diverse set of image completions and we allow users to select among them. We demonstrate the superiority of our algorithm over existing image completion approaches.

Paper

SIGGRAPH paper. (pdf, 11MB)

Communications of the ACM paper. (pdf, 15MB) with Technical Perspective by Marc Levoy.

Presentation

.zip file (ppt + movies), 90MB

Citation

James Hays, Alexei A. Efros. Scene Completion Using Millions of Photographs. ACM Transactions on Graphics (SIGGRAPH 2007). August 2007, vol. 26, No. 3.
Bibtex

Data

Test set, 44MB containing 51 image/mask pairs used for our user study.
Additional test cases, 22MB. 27 more pairs.
User study materials, 184MB. Input image/masks, results from our algorithm, results from Criminisi et al., and Matlab code to run and analyze user studies on these sets of images.

Image Downloading Code

Code for downloading Flickr images.

Implementations

I'm aware of two class projects which implemented Scene Completion with smaller data sets. The results are very interesting.

Funding

This research is supported in part by:

NSF Graduate Research Fellowship to James Hays.
NSF grant CAREER IIS-0546547.
NSF grant CCF-0541230.

介绍一篇不错的文章-PhotoSketch: Internet Image Montage

丕子 — Fri, 02 Oct 2009 02:02:46 +0000

原文：http://cg.cs.tsinghua.edu.cn:8080/cmm/?page_id=155

PhotoSketch: Internet Image Montage

Tao Chen ¹ Ming-Ming Cheng ¹ Ping Tan ² Ariel Shamir ³ Shi-Min Hu ¹

¹ TNList, Department of Computer Science and Technology, Tsinghua University

² National University of Singapore ³ The Interdisciplinary Center

Abstract: We present a system that composes a realistic picture from a simple freehand sketch annotated with text labels. The composed picture is generated by seamlessly stitching several photographs in agreement with the sketch and text labels; these are found by searching the Internet. Although online image search generates many inappropriate results, our system is able to automatically select suitable photographs to generate a high quality composition, using a filtering scheme to exclude undesirable images. We also provide a novel image blending algorithm to allow seamless image composition. Each blending result is given a numeric score, allowing us to find an optimal combination of discovered images. Experimental results show the method is very successful; we also evaluate our system using the results from two user studies.

您可能也喜欢：
IJCAI 2011 accepted papers 出来了	CVPR2011录取结果	Tomasz：cvpr 2011: highlights from day 1	CVPR 2011 Best Paper-优秀论文	Single Image Haze Removal(图像去雾)-CVPR’09 Best Paper
无觅

您可能也喜欢：
SIGGRAPH 2010–虚拟的虫子	实时的自动变脸技术	Kinnect真是一枝独秀啊	[图] 若干年前做的玩的模型，业余者	SIGGRAPH 2010: 微软的模糊照片自动处理
无觅

您可能也喜欢：
SIGGRAPH 2010–虚拟的虫子	SIGGRAPH 2010论文：碎裂声音预测与合成	SIGGRAPH 2010 papers &浙大周昆及学生的几篇论文	介绍一篇不错的文章-PhotoSketch: Internet Image Montage	微软新概念混合鼠标
无觅

您可能也喜欢：
SIGGRAPH 2010论文：碎裂声音预测与合成	SIGGRAPH 2010: 微软的模糊照片自动处理	[Paper] 一篇SiGGRAPH09的文章：PatchMatch	SIGGRAPH 2010 papers &浙大周昆及学生的几篇论文	SIGGRAPH’10的一篇论文–NETRA:视力自动评测和矫正
无觅

您可能也喜欢：
[Paper] 一篇SiGGRAPH09的文章：PatchMatch	SIGGRAPH 2010论文：碎裂声音预测与合成	SIGGRAPH 2010–虚拟的虫子	SIGGRAPH 2010: 微软的模糊照片自动处理	SIGGRAPH 2010 papers &浙大周昆及学生的几篇论文
无觅

您可能也喜欢：
最近图像检索应用的新闻	Google新图像检索发布视频	再次关注Google图像检索–嵌入广告	图像查询的特点(Characteristics of image queries)	介绍一个手绘图像检索的引擎，说实话，一点儿都不准
无觅

丕子 » SIGGRAPH

SIGGRAPH2011和IJCAI2011关于CV的Paper

Robotics and Vision

State-of-the-Art Reports

Session: Quality and Scalability

Session: Non-Photorealistic Rendering

Session: Image and Video

相关文章

GRAPH：想改变现实么？

相关文章

SIGGRAPH 2010: 微软的模糊照片自动处理

相关文章

SIGGRAPH 2010--虚拟的虫子

相关文章

SIGGRAPH'10的一篇论文--NETRA:视力自动评测和矫正

NETRA: Interactive Display for Estimating

Refractive Errors and Focal Range

Abstract

Paper

Videos

Pictures

相关文章

SIGGRAPH 2010 papers &浙大周昆及学生的几篇论文

相关文章

[Paper] 一篇SiGGRAPH09的文章：PatchMatch

相关文章

浙大周昆中４篇SIGGRAPH Asia 2009（被TOG收录）

相关文章

Scene Completion Using Millions of Photographs

Scene Completion Using Millions of Photographs

People

Abstract

Paper

Presentation

Citation

Data

Image Downloading Code

Implementations

Funding

相关文章

介绍一篇不错的文章-PhotoSketch: Internet Image Montage

PhotoSketch: Internet Image Montage

相关文章