Combining Silhouette and Shading Cues for Model Reconstruction

by Shuda Li, 李書達 (Creator)

This dissertation, "Combining Silhouette and Shading Cues for Model Reconstruction" by Shuda, Li, 李書達, was obtained from The University of Hong Kong (Pokfulam, Hong Kong) and is being sold pursuant to Creative Attribution 3.0 Hong Kong License. The content of this dissertation has not been altered in any way. We have altered the formatting in order to facilitate the ease of printing and reading of the dissertation. All rights not granted by the above license are retained by the author.Abstract of thesis entitled "Combining Silhouette and Shading Cues for Model Reconstruction" Submitted by Shuda Li for the degree of Master of Philosophy at the University of Hong Kong in September 2006 This work deals with the problems of scene illumination estimation and shape re- covery from an image sequence of a smooth textureless object. A novel method that exploits the contour generators estimated from the silhouettes for recovering the scene illumination is introduced. Compared with previous methods which are based on sparse frontier points or sampling from the visual hull mesh, the proposed method makes use of the geometrical information provided by the abundant contour generator points, and allows a closed-form solution with high precision. Using the estimated illumination, an algorithm for optimizing the visual hull mesh constructed from the silhouettes is developed. It evolves the mesh by iteratively estimating both the surface normal and depth that maximize the photometric consistency across the sequence. Compared with previous studies which optimized the mesh by estimating the surface normal alone, the proposed method shows better convergence and can recover better surface details, especially when concavities are deep and sharp. (187 words)10.5353/th_b3963425Computer visionImage processing - Data processing

72 pages, Hardcover

Published January 27, 2017