Spatiotemporal Texture Reconstruction for Dynamic Objects Using a Single RGB-D Camera

TL;DR

This paper introduces a method to generate dynamic, time-varying textures for moving objects using a single RGB-D camera by formulating the problem as an MRF optimization, effectively capturing the object's appearance over time.

Contribution

It proposes a novel framework that reconstructs plausible spatiotemporal textures for dynamic objects from a single RGB-D sequence, addressing occlusions and invisible areas.

Findings

Spatiotemporal textures better reproduce object appearances than single textures.

The MRF-based approach effectively fills in occluded regions across frames.

Experimental results validate the method's ability to generate consistent dynamic textures.

Abstract

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.