Robotics and Computer Vision Lab

Publications

조회 수 1438 댓글 0
Extra Form
저 자 Tae-Hyun Oh, Hyeongwoo Kim, Yu-Wing Tai, Jean-Charles Bazin, In So Kweon
학 회 IEEE International Conference on Computer Vision (ICCV)
Notes Ack: NCRC, This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government( MEST) (No. 2010-0028680).
논문일시(Year) 2013
논문일시(Month) 12
Project Page at http://thoh.kaist.ac.kr

Robust Principal Component Analysis (RPCA) via rank minimization is a powerful tool for recovering underlying low-rank structure of clean data corrupted with sparse noise/outliers. In many low-level vision problems, not only it is known that the underlying structure of clean data is low-rank, but the exact rank of clean data is also known. Yet, when applying conventional rank minimization for those problems, the objective function is formulated in a way that does not fully utilize a priori target rank information about the problems. This observation motivates us to investigate whether there is a better alternative solution when using rank minimization.
In this paper, instead of minimizing the nuclear norm, we propose to minimize the partial sum of singular values. The proposed objective function implicitly encourages the target rank constraint in rank minimization. Our experimental analyses show that our approach performs better than conventional rank minimization when the number of samples is deficient, while the solutions obtained by the two approaches are almost identical when the number of samples is more than sufficient. We apply our approach to various low-level vision problems, e.g. high dynamic range imaging, photometric stereo and image alignment, and show that our results outperform those obtained by the conventional nuclear norm rank minimization method.


[BibTex]

@inproceedings{thoh:iccv13,
author = {Tae-Hyun Oh and Hyeongwoo Kim and Yu-Wing Tai and Jean-Charles Bazin and In So Kweon },
title = {Partial Sum Minimization of Singular Values in {RPCA} for Low-Level Vision},
booktitle = {{IEEE} International Conference on Computer Vision (ICCV)},
year = {2013},
}

List of Articles
388. 도로 상의 특징점을 이용한 단일 카메라 기반의 차량 자세 추정
Jongwon Choi, Tae-Hyun Oh, In So Kweon
제 26 회 영상처리 및 이해에 관한 워크샵 (IPIU 2014) 2014 / 02
387. 다중 정보 융합 비용 체적을 이용한 라이트 필드 카메라에서의 깊이지도 추정
Min Jung Kim, Tae-Hyun Oh, In So Kweon
제 26 회 영상처리 및 이해에 관한 워크샵 (IPIU 2014) 2014 / 02
386. PRISM: A System for Weighted Multi-Color Browsing of Fashion Products
Donggeun Yoo, Kyunghyun Paeng, Sunggyun Park, Jungin Lee, Seungwook Paek, Sung-Eui Yoon, In So Kweon
International World Wide Web Conference (WWW) Companion 2014 / 04
385. Noise aware depth denoising for a time-of-flight camera
Jiyoung Jung, Joon-Young Lee, In So Kweon
20th Korea-Japan Joint Workshop on Frontiers of Computer Vision 2014 / 02
384. P-RIF: Perceptually Robust Invariant Feature
Sungho Kim, In So Kweon
IPIU 2013 / 02
383. A Perceptual Visual Feature Extraction Method Achieved by Imitating V1 and V4 of the Human Visual System
Sungho Kim, 권순, In So Kweon
Cognitive Computation 2012 / 11
382. Image-Optimized Rolling Cache: Reducing the Miss Penalty for Memory-Intensive Vision Algorithms
Younggeun Kim, In So Kweon
IEEE Transactions on Circuits and Systems for Video Technology 2013 / 12
381. Robust Computer Vision Techniques for High-quality 3D Modeling
Joon-Young Lee, Jiyoung Jung, Yunsu Bok, Jaesik Park, Dong-Geol Choi, Yudeog Han, In So Kweon
IAPR Asian Conference on Pattern Recognition 2013 / 11
380. Orientation based multi-scale corner detection for mobile robot application
Sungho Kim, In So Kweon, Wangheon Lee
International Conference on Control, Automation and Systems 2012 / 10
379. Omnidirectional Object Recognition Based Mobile Robot Localization
Sungho Kim, In So Kweon
Lecture Notes in Electrical Engineering 2013 / 05
378. Model-Based Scene Interpretation by Multilayered Context Information. In N.M.Seel(Ed.), Encyclopedia of the Science of Learning
Sungho Kim, In So Kweon
Springer 2012 / 01
377. Feature point detection by combining advantages of intensity-based approach and edge-based approach
Sungho Kim, Chaehoon Park, Yukyung Choi, 권순, In So Kweon
World Academy of Science Engineering and Technology 2012 / 08
376. 영상 곡률 공간 정보를 이용한 코너 검출 기법
Sungho Kim, Chaehoon Park, Yukyung Choi, In So Kweon
2011 제 26회 ICROS 학술대회 2011 / 05
375. TVF와 GVF를 이용한 특징점 추출
Sungho Kim, Chaehoon Park, Yukyung Choi, In So Kweon
신호처리종합학술대회 2011 / 09
374. 컬러영상분할을 이용한 향상된 안개제거
Sang-Woo Noh, Byungtae Ahn, In So Kweon
신호처리합동학술대회 2013 / 10
373. Appearance-based Gaze Estimation using Kinect
Jinsoo Choi, Byungtae Ahn, Jaesik Park, In So Kweon
The 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI 2013) 2013 / 10
372. Haze Removal on Superpixel Domain
Sang-Woo Noh, Byungtae Ahn, In So Kweon
The 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI) 2013 / 10
» Partial Sum Minimization of Singular Values in RPCA for Low-Level Vision
Tae-Hyun Oh, Hyeongwoo Kim, Yu-Wing Tai, Jean-Charles Bazin, In So Kweon
IEEE International Conference on Computer Vision (ICCV) 2013 / 12
370. High Quality Shape from a Single RGB-D Image under Uncalibrated Natural Illumination
Yudeog Han, Joon-Young Lee, In So Kweon
IEEE International Conference on Computer Vision (ICCV) 2013 / 12
369. Multiview Photometric Stereo using Planar Mesh Parameterization
Jaesik Park, Sudipta N. Sinha, Yasuyuki Matsushita, Yu-Wing Tai, In So Kweon
IEEE International Conference on Computer Vision (ICCV) 2013 / 12
Board Pagination Prev 1 ... 7 8 9 10 11 12 13 14 15 16 ... 31 Next
/ 31