2026-04-14T03:50:43Zhttps://recercat.cat/oai/request

oai:recercat.cat:10230/358252025-12-19T23:03:18Zcom_2072_6col_2072_452952

00925njm 22002777a 4500 dc Haro Ortega, Gloria author 2018-11-22T10:19:45Z 2018-11-22T10:19:45Z 2014 Comunicació presentada al congrés IEEE International Conference on Image Processing (ICIP) celebrat del 27 al 30 d'octubre de 2018 a Paris, França. We propose a 3D reconstruction algorithm based on silhouettes and color images. It is robust to inconsistent silhouettes, often common in real applications due to occlusions, errors in the background subtraction, noise or even calibration errors. The recovery of the shape that best fits the available data is formulated as a continuous energy minimization problem. The energy is based on the error between the silhouettes and the shape plus a regularization term based on a photo-consistency measure that places the surface at photo-consistent locations. The visibility is modeled as a function of the shape. The proposed photo-consistency measure takes visibility into account, although the presented variational framework can use different photo-consistency computations. 3D reconstruction Multi-view Shape from silhouette Photo-consistency Visibility Shape from silhouette consensus and photo-consistency