Self-Supervised Joint Learning Framework of Depth Estimation via Implicit Cues

TL;DR

This paper introduces a self-supervised joint learning framework for monocular depth estimation that leverages dynamic and static cues from consecutive video frames, improving accuracy especially for dynamic objects.

Contribution

It proposes an implicit depth cue extractor and a high-dimensional attention module to enhance depth prediction by utilizing motion and geometric scene cues.

Findings

Outperforms state-of-the-art methods on KITTI and Make3D datasets.

Effectively captures dynamic scene information for improved depth estimation.

Enhances robustness of depth predictions through novel attention mechanisms.

Abstract

In self-supervised monocular depth estimation, the depth discontinuity and motion objects' artifacts are still challenging problems. Existing self-supervised methods usually utilize a single view to train the depth estimation network. Compared with static views, abundant dynamic properties between video frames are beneficial to refined depth estimation, especially for dynamic objects. In this work, we propose a novel self-supervised joint learning framework for depth estimation using consecutive frames from monocular and stereo videos. The main idea is using an implicit depth cue extractor which leverages dynamic and static cues to generate useful depth proposals. These cues can predict distinguishable motion contours and geometric scene structures. Furthermore, a new high-dimensional attention module is introduced to extract clear global transformation, which effectively suppresses uncertainty of local descriptors in high-dimensional space, resulting in a more reliable optimization in learning framework. Experiments demonstrate that the proposed framework outperforms the state-of-the-art(SOTA) on KITTI and Make3D datasets.