Consistent Binocular Depth and Scene Flow with Chained Temporal Profiles

Chun Ho Hung         Li Xu          Jiaya Jia

We propose a depth and image scene flow estimation method taking the input of a binocular video. The key component is motion-depth temporal consistency preservation, making computation in long sequences reliable. We tackle a number of fundamental technical issues, including connection establishment between motion and depth, structure consistency preservation in multiple frames, and long-range temporal constraint employment for error correction. We address all of them in a unified depth and scene flow estimation framework. Our main contributions include development of motion trajectories, which robustly link frame correspondences in a voting manner, rejection of depth/motion outliers through temporal robust regression, novel edge occurrence map estimation, and introduction of anisotropic smoothing priors for proper regularization.

Supplementary Video

[Download (.mp4, 104M)]

Or you can choose to view it online: