Saved in:
Bibliographic Details
Main Authors: Zuo, Yiming, Deng, Jia
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.11711
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909225509191680
author Zuo, Yiming
Deng, Jia
author_facet Zuo, Yiming
Deng, Jia
contents Depth completion is the task of generating a dense depth map given an image and a sparse depth map as inputs. It has important applications in various downstream tasks. 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_11711
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations
Zuo, Yiming
Deng, Jia
Computer Vision and Pattern Recognition
Depth completion is the task of generating a dense depth map given an image and a sparse depth map as inputs. It has important applications in various downstream tasks. 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.
title OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.11711