Learning Conditional Random Fields for Stereo

TLDR

Stereo vision algorithms rely on color changes for object boundaries and often use heuristic disparity priors modulated by intensity gradients. The study aims to replace these heuristic priors with probabilistic models of disparities and intensities learned from real images. The authors built extensive stereo datasets with ground‑truth disparities and used a subset to learn conditional random field parameters. Experiments show that the learned CRF models can automatically capture richer structure than hand‑tuned MRFs.

Abstract

State-of-the-art stereo vision algorithms utilize color changes as important cues for object boundaries. Most methods impose heuristic restrictions or priors on disparities, for example by modulating local smoothness costs with intensity gradients. In this paper we seek to replace such heuristics with explicit probabilistic models of disparities and intensities learned from real images. We have constructed a large number of stereo datasets with ground-truth disparities, and we use a subset of these datasets to learn the parameters of conditional random fields (CRFs). We present experimental results illustrating the potential of our approach for automatically learning the parameters of models with richer structure than standard hand-tuned MRF models.