2010年图像视频影视后期制作外文翻译--视频后期制作的高分辨率图像对应

《2010年图像视频影视后期制作外文翻译--视频后期制作的高分辨率图像对应》由会员分享，可在线阅读，更多相关《2010年图像视频影视后期制作外文翻译--视频后期制作的高分辨率图像对应（21页珍藏版）》请在毕设资料网上搜索。

1、4100 英文单词，英文单词，2.2 万英文字符万英文字符，中文中文 7200 字字 文献出处文献出处: Lipski C, Linz C, Neumann T, et al. High resolution image correspondences for video Post-ProductionC/2010 Conference on Visual Media Production. IEEE, 2010: 33-39 HIGH RESOLUTION IMAGE CORRESPONDENCES FOR VIDEO POST-PRODUCTION C. Lipski, C.Linz, T

2、.Neumann, M.Wacker, M.Magnor Abstract We present an algorithm for estimating dense image correspondences. Our versatile approach lends itself to various tasks typical for video post-processing, including image morphing, optical flow estimation, stereo rectification, disparity/depth reconstruction an

3、d baseline adjustment. We incorporate recent advances in feature matching, energy minimization, stereo vision and data clustering into our approach. At the core of our correspondence estimation we use Efficient Belief Propagation for energy minimization. While state-of-the-art algorithms only work o

4、n thumbnail- sized images, our novel feature downsampling scheme in combination with a simple, yet efficient data term compression can cope with high-resolution data. The incorporation of SIFT features into data term computation further resolves matching ambiguities, making long-range correspondence

5、 estimation possible. We detect occluded areas by evaluating the correspondence symmetry, we further apply Geodesic matting to automatically inpaint these regions. Keywords: Video Post-Production, Optical Flow, Depth Reconstruction, Belief Propagation, Dense Image Correspondences 1. Introduction Est

6、ablishing dense image correspondences between images is still a challenging problem, especially when the input images feature long-range motion and large occluded areas. With the increasing availability of high-resolution content, the requirements for correspondence estimation between images are further increased. High resolution images often exhibit many ambiguous details, where their low resolution predecessors only show uniformly colored areas, thus the need for smarter and more robust ma