Non-Local Spatial Propagation Network for Depth Completion
By Jinsun Park, Kyungdon Joo, Zhe Hu, Chi Liu, In-So Kweon. European Conference on Computer Vision, 2020
424 citations recorded by the source corpus.
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.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/bd12ae924fc67465d69a9263f4f9dcb74d09de9d
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
Citations in the corpus
- PENet: Towards Precise and Efficient Image Guided Depth Completion (2021, methodology): “To dynamically learn the convolutional kernels, CSPN++ [7] and NLSPN [19] are proposed very recently.”
- Metric3D v2: A Versatile Monocular Geometric Foundation Model for Zero-Shot Metric Depth and Surface Normal Estimation (2024, positive): “Deep iterative refinement for geometry: Iterative refinement enables multi-step coarse-to-fine prediction and benefits a wide range of geometry estimation tasks, such as optical flow estimation [46], [75], [76], depth completion [43], [77], [78], and stereo matching [45], [79], [80].”