CVJul 20, 2020

Non-Local Spatial Propagation Network for Depth Completion

arXiv:2007.10042v1411 citations
Originality Incremental advance
AI Analysis

This work addresses the mixed-depth problem in depth completion for computer vision applications, offering an incremental improvement over existing methods by focusing on non-local neighbors.

The paper tackles depth completion by proposing a non-local spatial propagation network that uses RGB and sparse depth images to estimate non-local neighbors and affinities, iteratively refining depth predictions to avoid irrelevant local neighbors and address the mixed-depth problem on boundaries. Experimental results show superior accuracy and robustness compared to conventional algorithms on indoor and outdoor datasets.

In this paper, we propose a robust and efficient end-to-end non-local spatial propagation network for depth completion. The proposed network takes RGB and sparse depth images as inputs and estimates non-local neighbors and their affinities of each pixel, as well as an initial depth map with pixel-wise confidences. The initial depth prediction is then iteratively refined by its confidence and non-local spatial propagation procedure based on the predicted non-local neighbors and corresponding affinities. Unlike previous algorithms that utilize fixed-local neighbors, the proposed algorithm effectively avoids irrelevant local neighbors and concentrates on relevant non-local neighbors during propagation. In addition, we introduce a learnable affinity normalization to better learn the affinity combinations compared to conventional methods. The proposed algorithm is inherently robust to the mixed-depth problem on depth boundaries, which is one of the major issues for existing depth estimation/completion algorithms. Experimental results on indoor and outdoor datasets demonstrate that the proposed algorithm is superior to conventional algorithms in terms of depth completion accuracy and robustness to the mixed-depth problem. Our implementation is publicly available on the project page.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes