|
Image / Video Texture Editing
|
|
We propose a novel image/video retexturing approach that preserves the original shading effects without knowing the underlying surface and lighting conditions. For static images, we first introduce the Poisson equation-based algorithm to simulate the texture distortion on the projected interest region of the underlying surface, while preserving the shading effect of the original image. We further work on videos by retexturing the key frame as static image and then propagating the results onto the other frames. In video retexturing, we have introduced the mesh based optimization for object tracking to avoid texture drifting, and the graph cut algorithm to effectively deal with visibility shift between frames. The graph cut algorithm is applied on a trimap along the boundary of the object to extract the textured part inside the trimap. The proposed approach is developed in image/video retexturing at nearly interactive rate, and our experimental results have showed the satisfactory performance of our approach. |
| Examples of our system: |
|
|
|
Image retexturing results. Left: original images. Right: retextured results |
|
|
|
Part of the frames of our video retexturing results |
|
|
|
Our system UI.. |
| Download a demo (video) here! |
|
Paper: Yanwen Guo, Jin Wang, Xiang Zeng, Zhongyi Xie, Hanqiu Sun, Qunsheng Peng, Image and Video Retexturing. CASA 2005 (International Conference), Also In: International Journal of Computer Animation and Virtual Worlds (CAVW) , 2005, 16(3), pp. 451-461. (SCI, EI, ISTP) [PDF, 544K] |
|
|
|
We presents an approach of replacing textures of
specified regions in the input image/video with the new ones. The replacement results have the similar distortion and shading effects conforming to the unknown underlying geometry and lighting conditions. For replacing textures in single image, the approach consists of two important steps. First, a stretch-based mesh parametrization incorporating the recovered normal information is deduced to imitate the perspective distortion of the interest region. Second, a Poisson-based refinement process is exploited to account for texture distortion at fine scale. The luminance of the input image is preserved through color transfer in YCbCr color space. Our approach is independent of the replaced textures. Once processing the input image is completed, any new texture can be applied for efficiently generating the replacement result. For dealing with video sequence, one key-frame based texture replacement approach is devised. The approach is generalized and extended from the approach of image retexturing. It repeatedly propagates the replacement results of the key frames to the rest ones. We develop a local motion optimization scheme to deal with the inaccuracies and errors of robust optical flow when tracking moving objects. One graphcut segmentation algorithm is incorporated into the approach for handling visibility shifting. Texture drifting is alleviated with one globally optimization to smooth trajectories of the tracked points over temporal domain. Experimental results show that our approach can generate visually pleasing results for both image and video. |
| Examples: |
|
|
|
Our results with variant replaced texture scales |
|
|
|
Replaced Effects with texture discontinuity in self-occlusion regions |
|
|
|
Virtual fashion results |
|
|
|
|
|
Image editing results |
|
Papers: Yanwen Guo, Hanqiu Sun, Qunsheng Peng, Zhongding Jiang, Mesh-Guided Optimized Retexturing for Image and Video. IEEE Transactions on Visualization and Computer Graphics. 2008, 14(2): 426-439 (IEEE TVCG, SCI, EI). Yanwen Guo, Hanqiu Sun, Qunsheng Peng, Gangshan Wu, Effective Mesh Optimization Based Texture Replacing on Image Space. Chinese Journal of Computers, 2007, 30(9) (郭延文, 孙汉秋, 彭群生, 武港山 基于网格优化的图像纹理替换方法, 计算机学报, 2007, 30(9)) (EI)
|
| Back to the homepage |
