Easy matting: A Stroke Based Approach for Continuous Image Matting
Yu Guan, Wei Chen, Xiao Liang, Zi'ang Ding, Qunsheng Peng
Journal Computer Graphics Forum (Proceedings of Eurographics 2006), 25(3):567-576

We propose an iterative energy minimization framework for interactive image matting. Our approach is easy in the sense that it is fast and requires only few user-specified strokes for marking the foreground and background. Beginning with the known region, we model the unknown region as a Markov Random Field (MRF) and formulate its energy in each iteration as the combination of one data term and one smoothness term. By automatically adjusting the weights of both terms during the iterations, the first-order continuous and feature-preserving result is rapidly obtained with several iterations. The energy optimization can be further performed in selected local regions for refined results. We demonstrate that our energy-driven scheme can be extended to video matting, with which the spatio-temporal smoothness is faithfully preserved. We show that the proposed approach outperforms previous methods in terms of both the quality and performance for quite challenging examples.

pdf video bibtex slides

Modelling and Rendering of Realistic Waterfall Scenes with Dynamic Texture Sprites
Yu Guan, Wei Chen, Lincan Zou, Long Zhang, Qunsheng Peng
Journal of Computer Animation and Virtual Worlds, 2006, 17(5): 573 - 583.


We propose an efficient approach for authoring dynamic and realistic waterfall scenes based on acquired video sequence. aditional video based techniques generate new images by synthesizing 2D samples, i.e., texture sprites chosen from video sequence. However, they are limited to one fixed viewpoint and cannot provide arbitrary walkthrough into 3D scenes. Our approach extends this scheme by synthesizing dynamic 2D texture sprites and projecting them into 3D space. We first generate a set of basis texture sprites, which capture the representative appearances and motions of waterfall scenes contained in the video sequence. To model the shape and motion of a new waterfall scene, we interactively construct a set of flow lines taking account of physical principles. Along each flow line, the basis texture sprites are manipulated and animated dynamically, yielding a sequence of dynamic texture sprites in 3D space.

pdf

Dynamic Anisotropic Occlusion
Yi Gong, Yubo Zhang, Wei Chen, Qunsheng Peng
In Proceedings of EUROGRAPHICS 2006 (Short Presentation)

pdf

An Approximate Image-Space Approach for Real-Time Rendering of Deformable Translucent Objects
Yi Gong, Wei Chen, Long Zhang, Yun Zeng, Qunsheng Peng
In Proc. of Computer Graphics International (CGI) 2006

Direct Volume Rendering of Volumetric Data of Proteins
Min Hu, Wei Chen, Tao Zhang, Qunsheng Peng
Proc. of Computer Graphics International 2006

Quasi-physical Simulation of Large-scale Dynamic Forest Scenes
Long Zhang, Songfang Song, Qifeng Tan, Wei Chen, Qunsheng Peng
Proc. of Computer Graphics International 2006

As-Consistent-As-Possible Compositing of Virtual Objects And Video Sequences
Guofeng Zhang, Xueying Qin, Xiaobo An, Wei Chen and Hujun Bao
Journal of Computer Animation and Virtual Worlds 2006


We present an efficient approach that merges the virtual objects into video sequences taken by a freely moving camera in a realistic manner. The composition is visually and geometrically consistent through three main steps. First, a robust camera tracking algorithm based on key frames is proposed, which precisely recovers the focal length with a novel multi-frame strategy. Next, the concerned 3D models of the real scenes are reconstructed by means of an extended multi-baseline algorithm. Finally, the virtual objects in the form of 3D models are integrated into the real scenes, with special cares on the interaction consistency including shadow casting, occlusions and object animation. A variety of experiments have been implemented, which demonstrate the robustness and efficiency of our approach.

pdf video

Multi-level Differential Surface Representation Based on Local Transformations
Dong Xu, Wei Chen, Hongxin Zhang and Hujun Bao
The Visual Computer


One crucial issue of multi-resolution surface representations is how to effectively record and reconstruct geometric details among surface levels. Standard multi-resolution techniques encode details directly as local displacements in the vertices, and may produce unplausible results when the base level endures large deformations. In this paper we propose an alternative detail representation and reconstruction scheme, based on local transformations on a per-triangle basis. While more storages are required, recording details as local transformations favors global coupling of geometric details and allows for large-scale surface manipulations. By modeling the scale components of the surface modifications as a set of deforming factors, detail-preserving reconstruction results are achieved naturally under very large deformations. Comprehensive experimental results verify the efficiency and robustness of our approach.

pdf

A Novel Unified Variational Image Editing Model
Xiang Zeng , Wei Chen, Qunsheng Peng
Journal of Computer Science and Technology (JCST)