Learning the local statistics of optical flow

Dan Rosenbaum, Daniel Zoran, Yair Weiss

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Motivated by recent progress in natural image statistics, we use newly available datasets with ground truth optical flow to learn the local statistics of optical flow and compare the learned models to prior models assumed by computer vision researchers. We find that a Gaussian mixture model (GMM) with 64 components provides a significantly better model for local flow statistics when compared to commonly used models. We investigate the source of the GMM's success and show it is related to an explicit representation of flow boundaries. We also learn a model that jointly models the local intensity pattern and the local optical flow. In accordance with the assumptions often made in computer vision, the model learns that flow boundaries are more likely at intensity boundaries. However, when evaluated on a large dataset, this dependency is very weak and the benefit of conditioning flow estimation on the local intensity pattern is marginal.

Original languageEnglish
Title of host publicationProceedings of the 27th Conference on Neural Information Processing Systems (NeurIPS)
StatePublished - 2013
Externally publishedYes
Event27th Annual Conference on Neural Information Processing Systems, NIPS 2013 - Lake Tahoe, NV, United States
Duration: 5 Dec 201310 Dec 2013

Publication series

NameAdvances in Neural Information Processing Systems
ISSN (Print)1049-5258

Conference

Conference27th Annual Conference on Neural Information Processing Systems, NIPS 2013
Country/TerritoryUnited States
CityLake Tahoe, NV
Period5/12/1310/12/13

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint

Dive into the research topics of 'Learning the local statistics of optical flow'. Together they form a unique fingerprint.

Cite this