Picture: A Probabilistic Programming Language for Scene Perception
Name
Tenenbaum_Picture A.pdf
Size
2.3 MB
Format
Adobe PDF
Checksum (MD5)
b4f3061e0504ff6b2e14a41eb789bdcf
Author(s)
Kulkarni, Tejas Dattatraya
Tenenbaum, Joshua B.
Mansinghka, Vikash K.
Kohli, Pushmeet
Date Issued
2015
Journal
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Kulkarni, Tejas D., Pushmeet Kohli, Joshua B. Tenenbaum, Vikash Mansinghka. "Picture: A Probabilistic Programming Language for Scene Perception." Forthcoming in the proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Hynes Convention Center, Boston, MA, June 7-12, 2015.
Version
Author's final manuscript
Abstract
Recent progress on probabilistic modeling and statistical learning, coupled with the availability of large training datasets, has led to remarkable progress in computer vision. Generative probabilistic models, or “analysis-by-synthesis” approaches, can capture rich scene structure but have been less widely applied than their discriminative counterparts, as they often require considerable problem-specific engineering in modeling and inference, and inference is typically seen as requiring slow, hypothesize-and-test Monte Carlo methods. Here we present Picture, a probabilistic programming language for scene understanding that allows researchers to express complex generative vision models, while automatically solving them using fast general-purpose inference machinery. Picture provides a stochastic scene language that can express generative models for arbitrary 2D/3D scenes, as well as a hierarchy of representation layers for comparing scene hypotheses with observed images by matching not simply pixels, but also more abstract features (e.g., contours, deep neural network activations). Inference can flexibly integrate advanced Monte Carlo strategies with fast bottom-up data-driven methods. Thus both representations and inference strategies can build directly on progress in discriminatively trained systems to make generative vision more robust and efficient. We use Picture to write programs for 3D face analysis, 3D human pose estimation, and 3D object reconstruction – each competitive with specially engineered baselines.
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
http://www.cv-foundation.org/openaccess/CVPR2015.py
