Spatiotemporal Texture Reconstruction for Dynamic Objects Using a Single RGB-D Camera
This work addresses texture reconstruction for dynamic objects in computer vision, but it is incremental as it builds on existing MRF optimization techniques.
The paper tackles the problem of reconstructing time-varying texture maps for dynamic objects from a single RGB-D camera by borrowing textures from invisible areas across frames, and demonstrates that their method better reproduces active appearances compared to single-texture approaches.
This paper presents an effective method for generating a spatiotemporal (time-varying) texture map for a dynamic object using a single RGB-D camera. The input of our framework is a 3D template model and an RGB-D image sequence. Since there are invisible areas of the object at a frame in a single-camera setup, textures of such areas need to be borrowed from other frames. We formulate the problem as an MRF optimization and define cost functions to reconstruct a plausible spatiotemporal texture for a dynamic object. Experimental results demonstrate that our spatiotemporal textures can reproduce the active appearances of captured objects better than approaches using a single texture map.