NDDepth: Normal-Distance Assisted Monocular Depth Estimation

TL;DR

NDDepth introduces a physics-inspired deep learning approach for monocular depth estimation, leveraging surface normals and plane distances with a novel refinement module, achieving state-of-the-art results on multiple datasets.

Contribution

The paper presents a new normal-distance head and a contrastive refinement module for improved monocular depth estimation, grounded in geometric assumptions.

Findings

Outperforms previous methods on NYU-Depth-v2, KITTI, and SUN RGB-D datasets.

Achieves 1st place on the KITTI depth prediction benchmark.

Effectively combines surface normal and depth refinement for robustness.

Abstract

Monocular depth estimation has drawn widespread attention from the vision community due to its broad applications. In this paper, we propose a novel physics (geometry)-driven deep learning framework for monocular depth estimation by assuming that 3D scenes are constituted by piece-wise planes. Particularly, we introduce a new normal-distance head that outputs pixel-level surface normal and plane-to-origin distance for deriving depth at each position. Meanwhile, the normal and distance are regularized by a developed plane-aware consistency constraint. We further integrate an additional depth head to improve the robustness of the proposed framework. To fully exploit the strengths of these two heads, we develop an effective contrastive iterative refinement module that refines depth in a complementary manner according to the depth uncertainty. Extensive experiments indicate that the proposed method exceeds previous state-of-the-art competitors on the NYU-Depth-v2, KITTI and SUN RGB-D datasets. Notably, it ranks 1st among all submissions on the KITTI depth prediction online benchmark at the submission time.