UFD-PRiME: Unsupervised Joint Learning of Optical Flow and Stereo Depth through Pixel-Level Rigid Motion Estimation

TL;DR

UFD-PRiME introduces an unsupervised joint learning framework for optical flow and stereo depth estimation, incorporating rigid motion of dynamic objects to improve accuracy and boundary details, outperforming previous methods on KITTI-2015.

Contribution

The paper presents the first unsupervised joint learning network for optical flow and stereo depth that also estimates rigid motions of dynamic objects.

Findings

Achieves 7.36% optical flow error on KITTI-2015, surpassing previous state-of-the-art.

Produces more detailed occlusions and object boundaries.

Provides competitive stereo depth results.

Abstract

Both optical flow and stereo disparities are image matches and can therefore benefit from joint training. Depth and 3D motion provide geometric rather than photometric information and can further improve optical flow. Accordingly, we design a first network that estimates flow and disparity jointly and is trained without supervision. A second network, trained with optical flow from the first as pseudo-labels, takes disparities from the first network, estimates 3D rigid motion at every pixel, and reconstructs optical flow again. A final stage fuses the outputs from the two networks. In contrast with previous methods that only consider camera motion, our method also estimates the rigid motions of dynamic objects, which are of key interest in applications. This leads to better optical flow with visibly more detailed occlusions and object boundaries as a result. Our unsupervised pipeline achieves 7.36% optical flow error on the KITTI-2015 benchmark and outperforms the previous state-of-the-art 9.38% by a wide margin. It also achieves slightly better or comparable stereo depth results. Code will be made available.