Photo collage is an effective representation for photo summarization and visualization. However, ... more Photo collage is an effective representation for photo summarization and visualization. However, its practical usage is limited by its high computational cost. In this paper, we present efficient optimization techniques based on a novel formulation on markov random fields and several insights unexploited by previous approaches. Our method achieves up to hundreds-fold performance improvement, and user/application specific constraints can be
General SFM methods give poor results for images captured by constrained motions such as planar m... more General SFM methods give poor results for images captured by constrained motions such as planar motion. In this paper, we propose new SFM algorithms for images captured under a common but constrained planar motion: the image plane is perpendicular to the motion plane. We show that a 2D image captured under such constrained planar motion can be decoupled into two
Concentric mosaics are low-dimensional lightfields. Yet capturing concentric mosaics requires a m... more Concentric mosaics are low-dimensional lightfields. Yet capturing concentric mosaics requires a motor-controlled device and it is not practical for real outdoor scenes. In this paper, we propose a new concentric mosaic construc- tion method by hand rotating an outward-looking camera. The geometry of such a capturing system is formulated as an outward-looking circular motion with unknown rotation angles. Then, a
Sketch matching is the fundamental problem in sketch based interfaces. After years of study, it r... more Sketch matching is the fundamental problem in sketch based interfaces. After years of study, it remains challenging when there exists large irregularity and variations in the hand drawn sketch shapes. While most existing works exploit topology relations and graph representations for this problem, they are usually limited by the coarse topology exploration and heuristic (thus suboptimal) similarity metrics between graphs. We present a new sketch matching method with two novel contributions. We introduce a comprehensive definition of topology relations, which results in a rich and informative graph representation of sketches. For graph matching, we propose topology product graph that retains the full correspondence for matching two graphs. Based on it, we derive an intuitive sketch similarity metric whose exact solution is easy to compute. In addition, the graph representation and new metric naturally support partial matching, an important practical problem that received less attention in the literature. Extensive experimental results on a real challenging dataset and the superior performance of our method show that it outperforms the state-of-the-art.
We propose a segmentation-based dense stereo algorithm within an energy minimization framework. T... more We propose a segmentation-based dense stereo algorithm within an energy minimization framework. The cost func- tion includes a new consistency term to take into account an initial quasi-dense disparity map and handles occlusions explicitly. Based on quasi-dense matching and color seg- mentation, optimization is performed efficiently by assum- ing a constant disparity for each region. The assumption is made robust
In this paper, we present an interactive offline tracking system for generic color objects. The s... more In this paper, we present an interactive offline tracking system for generic color objects. The system achieves 60- 100 fps on a 320 × 240 video. The user can therefore eas- ily refine the tracking result in an interactive way. To fully exploit user input and reduce user interaction, the track- ing problem is addressed in a global optimization frame-
ACM SIGGRAPH 2005 Sketches on - SIGGRAPH '05, 2005
ABSTRACT Hako-ne is an augmented reality hybrid art/technology project. Users will be able to see... more ABSTRACT Hako-ne is an augmented reality hybrid art/technology project. Users will be able to see characters of 3D musical notes moving on each side of the augmented musical dollhouse by using a handheld Optical See-Through Information Viewer (OSTV), which consists ...
Photo collage is an effective representation for photo summarization and visualization. However, ... more Photo collage is an effective representation for photo summarization and visualization. However, its practical usage is limited by its high computational cost. In this paper, we present efficient optimization techniques based on a novel formulation on markov random fields and several insights unexploited by previous approaches. Our method achieves up to hundreds-fold performance improvement, and user/application specific constraints can be
General SFM methods give poor results for images captured by constrained motions such as planar m... more General SFM methods give poor results for images captured by constrained motions such as planar motion. In this paper, we propose new SFM algorithms for images captured under a common but constrained planar motion: the image plane is perpendicular to the motion plane. We show that a 2D image captured under such constrained planar motion can be decoupled into two
Concentric mosaics are low-dimensional lightfields. Yet capturing concentric mosaics requires a m... more Concentric mosaics are low-dimensional lightfields. Yet capturing concentric mosaics requires a motor-controlled device and it is not practical for real outdoor scenes. In this paper, we propose a new concentric mosaic construc- tion method by hand rotating an outward-looking camera. The geometry of such a capturing system is formulated as an outward-looking circular motion with unknown rotation angles. Then, a
Sketch matching is the fundamental problem in sketch based interfaces. After years of study, it r... more Sketch matching is the fundamental problem in sketch based interfaces. After years of study, it remains challenging when there exists large irregularity and variations in the hand drawn sketch shapes. While most existing works exploit topology relations and graph representations for this problem, they are usually limited by the coarse topology exploration and heuristic (thus suboptimal) similarity metrics between graphs. We present a new sketch matching method with two novel contributions. We introduce a comprehensive definition of topology relations, which results in a rich and informative graph representation of sketches. For graph matching, we propose topology product graph that retains the full correspondence for matching two graphs. Based on it, we derive an intuitive sketch similarity metric whose exact solution is easy to compute. In addition, the graph representation and new metric naturally support partial matching, an important practical problem that received less attention in the literature. Extensive experimental results on a real challenging dataset and the superior performance of our method show that it outperforms the state-of-the-art.
We propose a segmentation-based dense stereo algorithm within an energy minimization framework. T... more We propose a segmentation-based dense stereo algorithm within an energy minimization framework. The cost func- tion includes a new consistency term to take into account an initial quasi-dense disparity map and handles occlusions explicitly. Based on quasi-dense matching and color seg- mentation, optimization is performed efficiently by assum- ing a constant disparity for each region. The assumption is made robust
In this paper, we present an interactive offline tracking system for generic color objects. The s... more In this paper, we present an interactive offline tracking system for generic color objects. The system achieves 60- 100 fps on a 320 × 240 video. The user can therefore eas- ily refine the tracking result in an interactive way. To fully exploit user input and reduce user interaction, the track- ing problem is addressed in a global optimization frame-
ACM SIGGRAPH 2005 Sketches on - SIGGRAPH '05, 2005
ABSTRACT Hako-ne is an augmented reality hybrid art/technology project. Users will be able to see... more ABSTRACT Hako-ne is an augmented reality hybrid art/technology project. Users will be able to see characters of 3D musical notes moving on each side of the augmented musical dollhouse by using a handheld Optical See-Through Information Viewer (OSTV), which consists ...
Uploads
Papers by Yichen Wei