IEBins: Iterative Elastic Bins for Monocular Depth Estimation

TL;DR

This paper introduces IEBins, an iterative elastic bin approach for monocular depth estimation that progressively refines depth predictions and adaptively adjusts bin widths to improve accuracy, outperforming previous methods.

Contribution

The paper proposes a novel iterative elastic bin framework with a GRU-based optimizer for improved monocular depth estimation accuracy.

Findings

Outperforms state-of-the-art on KITTI, NYU-Depth-v2, SUN RGB-D datasets.

Uses elastic target bins to reduce error accumulation.

Demonstrates effective depth refinement through multiple stages.

Abstract

Monocular depth estimation (MDE) is a fundamental topic of geometric computer vision and a core technique for many downstream applications. Recently, several methods reframe the MDE as a classification-regression problem where a linear combination of probabilistic distribution and bin centers is used to predict depth. In this paper, we propose a novel concept of iterative elastic bins (IEBins) for the classification-regression-based MDE. The proposed IEBins aims to search for high-quality depth by progressively optimizing the search range, which involves multiple stages and each stage performs a finer-grained depth search in the target bin on top of its previous stage. To alleviate the possible error accumulation during the iterative process, we utilize a novel elastic target bin to replace the original target bin, the width of which is adjusted elastically based on the depth uncertainty. Furthermore, we develop a dedicated framework composed of a feature extractor and an iterative optimizer that has powerful temporal context modeling capabilities benefiting from the GRU-based architecture. Extensive experiments on the KITTI, NYU-Depth-v2 and SUN RGB-D datasets demonstrate that the proposed method surpasses prior state-of-the-art competitors. The source code is publicly available at https://github.com/ShuweiShao/IEBins.