OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations

TL;DR

OGNI-DC introduces a novel optimization-guided neural iteration framework for depth completion, achieving state-of-the-art results with strong generalization across datasets and sparsity levels.

Contribution

The paper presents OGNI-DC, a new depth completion method combining neural refinement and differentiable depth integration for improved accuracy and robustness.

Findings

Outperforms baselines on unseen datasets.

Achieves state-of-the-art on NYUv2 and KITTI.

Demonstrates strong generalization across sparsity levels.

Abstract

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.