The Community for Technology Leaders
Green Image
This paper presents an approach of replacing textures of specified regions in the input image/video with new ones. The replacement results have the similar distortion and shading effects conforming to the underlying geometry and lighting conditions. For replacing textures in single image, the approach consists of two steps. First, a stretchbased mesh parametrization incorporating the recovered normal information is deduced to imitate perspective distortion of the interest region. Second, a Poisson-based refinement process is exploited to account for texture distortion at fine scale. Our approach is independent of the replaced textures. Once processing the input image is completed, any new texture can be applied efficiently. For dealing with video sequence, one key-frame based texture replacement approach is devised. The approach is generalized from image retexturing. It repeatedly propagates the replacement results of key frames to the rest ones. We develop a local motion optimization scheme to deal with the inaccuracies of 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.
Picture/Image Generation, Color, shading, shadowing, and texture, Image Processing and Computer Vision

Z. Jiang, Q. Peng, Y. Guo and H. Sun, "Mesh-Guided Optimized Retexturing for Image and Video," in IEEE Transactions on Visualization & Computer Graphics, vol. 14, no. , pp. 426-439, 2007.
92 ms
(Ver 3.3 (11022016))