3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-Labeling

TL;DR

This paper introduces a domain adaptation framework for monocular depth estimation that generates reliable pseudo ground truths from real data using 2D consistency and 3D-aware point cloud completion, improving performance over existing methods.

Contribution

It proposes a novel pseudo-labeling approach combining 2D consistency and 3D-aware point cloud completion for better domain adaptation in depth estimation.

Findings

Improved depth estimation accuracy across various datasets.

Effective use of stereo pairs during training.

Outperforms several state-of-the-art unsupervised domain adaptation methods.

Abstract

For monocular depth estimation, acquiring ground truths for real data is not easy, and thus domain adaptation methods are commonly adopted using the supervised synthetic data. However, this may still incur a large domain gap due to the lack of supervision from the real data. In this paper, we develop a domain adaptation framework via generating reliable pseudo ground truths of depth from real data to provide direct supervisions. Specifically, we propose two mechanisms for pseudo-labeling: 1) 2D-based pseudo-labels via measuring the consistency of depth predictions when images are with the same content but different styles; 2) 3D-aware pseudo-labels via a point cloud completion network that learns to complete the depth values in the 3D space, thus providing more structural information in a scene to refine and generate more reliable pseudo-labels. In experiments, we show that our pseudo-labeling methods improve depth estimation in various settings, including the usage of stereo pairs during training. Furthermore, the proposed method performs favorably against several state-of-the-art unsupervised domain adaptation approaches in real-world datasets.