Paper Info
Title
Learning to Exploit Stability for 3D Scene Parsing.
Abstract
Human scene understanding uses a variety of visual and non-visual cues to perform inference on object types, poses, and relations. Physics is a rich and universal cue that we exploit to enhance scene understanding. In this paper, we integrate the physical cue of stability into the learning process by looping in a physics engine into bottom-up recognition models, and apply it to the problem of 3D scene parsing. We first show that applying physics supervision to an existing scene understanding model increases performance, produces more stable predictions, and allows training to an equivalent performance level with fewer annotated training examples. We then present a novel architecture for 3D scene parsing named Prim R-CNN, learning to predict bounding boxes as well as their 3D size, translation, and rotation. With physics supervision, Prim R-CNN outperforms existing scene understanding approaches on this problem. Finally, we show that finetuning with physics supervision on unlabeled real images improves real domain transfer of models training on synthetic data.
Year
Venue
Keywords
2018
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018)
learning process,synthetic data,3d scene,physics engine,object types
Field
DocType
Volume
Inference,Physics engine,Computer science,Object type,Exploit,Synthetic data,Artificial intelligence,Parsing,Real image,Machine learning,Bounding overwatch
Conference
31
ISSN
Citations 
PageRank 
1049-5258
2
0.36
References 
Authors
0
7
Name
Order
Citations
PageRank
Yilun Du1107.56
Zhijian Liu2599.80
Basevi, Hector320.36
Ales Leonardis41636147.33
Freeman, Bill591.14
Joshua B. Tenenbaum64445437.33
Yichen Wei781447.77