Self-Supervised Monocular Depth Estimation by Direction-aware Cumulative Convolution Network

TL;DR

This paper introduces DaCCN, a novel network that enhances self-supervised monocular depth estimation by incorporating direction-aware modules and cumulative convolutions, leading to state-of-the-art results across multiple benchmarks.

Contribution

The paper proposes a direction-aware cumulative convolution network (DaCCN) that improves feature representation for depth estimation by encoding environmental information more effectively.

Findings

Achieves new state-of-the-art performance on KITTI, Cityscapes, and Make3D datasets.

Demonstrates significant accuracy improvements over existing methods.

Effectively encodes environmental information through novel modules.

Abstract

Monocular depth estimation is known as an ill-posed task in which objects in a 2D image usually do not contain sufficient information to predict their depth. Thus, it acts differently from other tasks (e.g., classification and segmentation) in many ways. In this paper, we find that self-supervised monocular depth estimation shows a direction sensitivity and environmental dependency in the feature representation. But the current backbones borrowed from other tasks pay less attention to handling different types of environmental information, limiting the overall depth accuracy. To bridge this gap, we propose a new Direction-aware Cumulative Convolution Network (DaCCN), which improves the depth feature representation in two aspects. First, we propose a direction-aware module, which can learn to adjust the feature extraction in each direction, facilitating the encoding of different types of information. Secondly, we design a new cumulative convolution to improve the efficiency for aggregating important environmental information. Experiments show that our method achieves significant improvements on three widely used benchmarks, KITTI, Cityscapes, and Make3D, setting a new state-of-the-art performance on the popular benchmarks with all three types of self-supervision.