dc.citation.conferencePlace |
UK |
- |
dc.citation.conferencePlace |
Online |
- |
dc.citation.title |
European Conference on Computer Vision |
- |
dc.contributor.author |
Park, Jinsun |
- |
dc.contributor.author |
Joo, Kyungdon |
- |
dc.contributor.author |
Hu, Zhe |
- |
dc.contributor.author |
Liu, Chi-Kuei |
- |
dc.contributor.author |
Kweon, In So |
- |
dc.date.accessioned |
2024-01-31T22:40:01Z |
- |
dc.date.available |
2024-01-31T22:40:01Z |
- |
dc.date.created |
2020-11-05 |
- |
dc.date.issued |
2020-08-23 |
- |
dc.description.abstract |
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. |
- |
dc.identifier.bibliographicCitation |
European Conference on Computer Vision |
- |
dc.identifier.uri |
https://scholarworks.unist.ac.kr/handle/201301/78269 |
- |
dc.publisher |
ECCV |
- |
dc.title |
Non-Local Spatial Propagation Network for Depth Completion |
- |
dc.type |
Conference Paper |
- |
dc.date.conferenceDate |
2020-08-23 |
- |