OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations
Abstract
Depth completion is the task of generating a dense depth map given an image and a sparse depth map as inputs. In this paper, we present OGNI-DC, a novel framework for depth completion. The key to our method is “Optimization-Guided Neural Iterations” (OGNI). It consists of a recurrent unit that refines a depth gradient field and a differentiable depth integrator that integrates the depth gradients into a depth map. OGNI-DC exhibits strong generalization, outperforming baselines by a large margin on unseen datasets and across various sparsity levels. Moreover, OGNI-DC has high accuracy, achieving state-of-the-art performance on the NYUv2 and the KITTI benchmarks. Code is available at https:// github.com/princeton-vl/OGNI-DC.
Cite
Text
Zuo and Deng. "OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-72646-0_5Markdown
[Zuo and Deng. "OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/zuo2024eccv-ognidc/) doi:10.1007/978-3-031-72646-0_5BibTeX
@inproceedings{zuo2024eccv-ognidc,
title = {{OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations}},
author = {Zuo, Yiming and Deng, Jia},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2024},
doi = {10.1007/978-3-031-72646-0_5},
url = {https://mlanthology.org/eccv/2024/zuo2024eccv-ognidc/}
}