Sciweavers

CVPR
2013
IEEE

3D-Based Reasoning with Blocks, Support, and Stability

9 years 11 months ago
3D-Based Reasoning with Blocks, Support, and Stability
3D volumetric reasoning is important for truly understanding a scene. Humans are able to both segment each object in an image, and perceive a rich 3D interpretation of the scene, e.g., the space an object occupies, which objects support other objects, and which objects would, if moved, cause other objects to fall. We propose a new approach for parsing RGB-D images using 3D block units for volumetric reasoning. The algorithm fits image segments with 3D blocks, and iteratively evaluates the scene based on block interaction properties. We produce a 3D representation of the scene based on jointly optimizing over segmentations, block fitting, supporting relations, and object stability. Our algorithm incorporates the intuition that a good 3D representation of the scene is the one that fits the data well, and is a stable, self-supporting (i.e., one that does not topple) arrangement of objects. We experiment on several datasets including controlled and real indoor scenarios. Results show t...
Zhaoyin Jia, Andrew C. Gallagher, Ashutosh Saxena,
Added 28 Apr 2014
Updated 28 Apr 2014
Type Journal
Year 2013
Where CVPR
Authors Zhaoyin Jia, Andrew C. Gallagher, Ashutosh Saxena, Tsuhan Chen
Comments (0)