A Segmentation Based Variational Model for Accurate Optical Flow Estimation (2009)
Li Xu, Jianing Chen, Jiaya Jia
Abstract. Segmentation has gained in popularity in stereo matching. However, it is not trivial to incorporate it in optical flow estimation due to the possible non-rigid motion problem. In this...
Recovering Consistent Video Depth Maps via Bundle Optimization (2009)
Guofeng Zhang, Jiaya Jia, Tien-tsin Wong, Hujun Bao
input sequence output video depth maps Figure 1. High-quality depth reconstruction from the video sequence “Road ” containing complex occlusions. Left: An input video sequence taken by a moving...
H.: Moving object extraction with a hand-held camera (2009)
Guofeng Zhang, Jiaya Jia, Wei Xiong, Tien-tsin Wong, Pheng-ann Heng, Hujun Bao
This paper presents a new method to detect and accurately extract the moving object from a video sequence taken by a hand-held camera. In order to extract the high quality moving foreground, previous...
Image Stitching Using Structure Deformation (2009)
Jiaya Jia, Chi-keung Tang, Senior Member, Ieee Computer Society
Abstract—The aim of this paper is to achieve seamless image stitching without producing visual artifact caused by severe intensity discrepancy and structure misalignment, given that the input...
Abstract Fast Image/Video Upsampling (2009)
Qi Shan, Zhaorong Li, Jiaya Jia, Chi-keung Tang
Figure 1: Local video upsampling. A magnifying effect is simulated by upsampling local regions using our algorithm. We propose a simple but effective upsampling method for automatically enhancing the...
Qi Shan, Jiaya Jia, Aseem Agarwala
Figure 1 High quality single image motion-deblurring. The left sub-figure shows one captured image using a hand-held camera under dim light. It is severely blurred by an unknown kernel. The right...
Stereo Matching: An Outlier Confidence Approach (2009)
Abstract. One of the major challenges in stereo matching is to handle partial occlusions. In this paper, we introduce the Outlier Confidence (OC) which dynamically measures how likely one pixel is...
Moving Object Extraction with a Hand-held Camera (2009)
Guofeng Zhang, Jiaya Jia, Wei Xiong, Tien-tsin Wong, Pheng-ann Heng, Hujun Bao
This paper presents a new method to detect and accurately extract the moving object from a video sequence taken by a hand-held camera. In order to extract the high quality moving foreground, previous...
IEEE Computer Society, and (2008)
Jiaya Jia, Ieee Computer Society
IEEE Computer Society Abstract—This paper presents a complete system capable of synthesizing a large number of pixels that are missing due to occlusion or damage in an uncalibrated input video....
Soft Color Segmentation and Its Applications (2008)
Yu-wing Tai, Student Member, Jiaya Jia, Ieee Computer Society, Chi-keung Tang, Senior Member, ...
Abstract—We propose an automatic approach to soft color segmentation, which produces soft color segments with an appropriate amount of overlapping and transparency essential to synthesizing natural...
To appear in the ACM SIGGRAPH conference proceedings Poisson Matting (2008)
Jian Sun, Jiaya Jia, Chi-keung Tang, Heung-yeung Shum
Figure 1: Pulling of matte from a complex scene. From left to right: a complex natural image for existing matting techniques where the color background is complex, a high quality matte generated by...
Active Window Oriented Dynamic Video (2008)
Chenjun Tao, Jiaya Jia, Hanqiu Sun
Abstract. When playing high-resolution videos on mobile devices with a limited screen size, a commonly arisen but seldom addressed problem is how to naturally condense the source video and to...
Prof Michael, R. Lyu, Prof Leo, Jiaya Jia
� Importance • Imperative due to explosive growth of image and video data • Far from mature compared with text information retrieval
Image stitching using structure deformation (2008)
The aim of this paper is to achieve seamless image stitching without producing visual artifact caused by severe intensity discrepancy and structure misalignment, given that the input images are...
Local color transfer via probabilistic segmentation by expectation-maximization (2005)
Tai, Yu-Wing, Jia, Jiaya, Tang, Chi-Keung
We address the problem of regional color transfer between two natural images by probabilistic segmentation. We use a new Expectation-Maximization (EM) scheme to impose both spatial and color...
Tensor voting for image correction by global and local intensity alignment (2005)
Jiaya Jia, Chi-keung Tang, Ieee Computer Society, Ieee Computer Society
Abstract—This paper presents a voting method to perform image correction by global and local intensity alignment. The key to our modeless approach is the estimation of global and local replacement...
Image completion with structure propagation (2005)
Jian Sun, Lu Yuan, Jiaya Jia, Heung-yeung Shum
two intersecting lines (green) specified by the user, (c) intermediate result after propagating structure and texture information along the user-specified lines, and (d) final result after filling in...
Tang “Local Color Transfer via Probabilistic Segmentation by Expectation-Maximization (2005)
Yu-wing Tai, Jiaya Jia, Chi-keung Tang
We address the problem of regional color transfer between two natural images by probabilistic segmentation. We use a new Expectation-Maximization (EM) scheme to impose both spatial and color...
Eliminating structure and intensity misalignment in image stitching (2005)
The aim of this paper is to achieve seamless image stitching for eliminating obvious visual artifact caused by severe intensity discrepancy, image distortion and structure misalignment, given that...
Image and video correction by ND tensor voting with intensity and structure consideration / (2004)
Thesis (Ph. D.)--Hong Kong University of Science and Technology, 2004.
Image and video correction by ND tensor voting with intensity and structure consideration (2004)
Thesis (Ph.D.)--Hong Kong University of Science and Technology, 2004
Image and video correction by ND tensor voting with intensity and structure consideration / (2004)
Thesis (Ph. D.)--Hong Kong University of Science and Technology, 2004.
Video repairing: Inference of foreground and background under severe occlusion (2004)
Jiaya Jia, Tai-pang Wu, Yu-wing Tai, Chi-keung Tang
In this paper, we propose a new method, video repairing, to robustly infer missing static background and moving foreground due to severe damage or occlusion from a video. To recover background...
Jian Sun, Jiaya Jia, Chi-keung Tang, Heung-yeung Shum
∗This research was done when Jiaya Jia was visiting MSR Asia. Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided...
Bayesian correction of image intensity with spatial consideration (2004)
Jiaya Jia, Jian Sun, Chi-keung Tang, Heung-yeung Shum
Abstract. Under dimly lit condition, it is difficult to take a satisfactory image in long exposure time with a hand-held camera. Despite the use of a tripod, moving objects in the scene still...
Image and video correction by ND tensor voting with intensity and structure consideration / (2004)
Thesis (Ph. D.)--Hong Kong University of Science and Technology, 2004.
Inference of segmented color and texture description by tensor voting (2004)
Jiaya Jia, Student Member, Chi-keung Tang, Ieee Computer Society
Abstract—A robust synthesis method is proposed to automatically infer missing color and texture information from a damaged 2D image by ND tensor voting (N>3). The same approach is generalized to...
Image repairing: Robust image synthesis by adaptive nd tensor voting (2003)
We present a robust image synthesis method to automatically infer missing information from a damaged 2D image by tensor voting. Our method translates image color and texture information into an...