Research map / 3D vision / Depth and stereo
OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration
Yiming Zuo, Willow Yang, Zeyu Ma, Jia Deng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use 3-resolution DDI instead of single-resolution DDI (ablation) | OMNI-DC · ETH3D-SfM validation | RMSE: 0.595 -> 0.459 | Improved |
| use 3-resolution DDI instead of single-resolution DDI (ablation) | OMNI-DC · KITTI-64 validation | RMSE: 1.210 -> 1.188 | Improved |
| add second resolution to DDI (ablation) | OMNI-DC · KITTI-64 validation | RMSE: 1.210 -> 1.218 | No clear effect |
| add Laplacian loss to L1 (ablation) | OMNI-DC · ETH3D-SfM validation | RMSE: 0.666 -> 0.598 | Improved |
| add gradient-matching loss to L1 (ablation) | OMNI-DC · ETH3D-SfM validation | RMSE: 0.666 -> 0.547 | Improved |
| add Laplacian loss to L1 + gradient-matching loss (ablation) | OMNI-DC · ETH3D-SfM validation | RMSE: 0.547 -> 0.490 | Improved |
| use log depth with median normalization instead of linear depth (ablation) | OMNI-DC · ETH3D-SfM validation | RMSE: 0.886 -> 0.490 | Improved |
| add median normalization to log depth (ablation) | OMNI-DC · KITTI-64 validation | RMSE: 1.293 -> 1.173 | Improved |
| add synthetic SfM/LiDAR sparse patterns to random sampling (ablation) | OMNI-DC · ETH3D-SfM validation | RMSE: 0.714 -> 0.647 | Improved |
| add outlier and boundary noise to training patterns (ablation) | OMNI-DC · ETH3D-SfM validation | RMSE: 0.647 -> 0.490 | Improved |
| mix NYUv2 real data into synthetic training (ablation) | OMNI-DC · zero-shot RMSE on KITTI-64L | RMSE: 1.279 -> 1.309 | Hurt |
| use OMNI-DC depth for 3DGS supervision instead of G2-MD | 3DGS · ETH3D novel view synthesis | PSNR: 19.36 -> 20.38 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- G2-MonoDepth — G2-MonoDepth: A General Framework of Generalized Depth Inference From Monocular RGB+X Data (TPAMI 2023) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior (AAAI 2025 · similarity 0.88)
- A Simple yet Universal Framework for Depth Completion (NeurIPS 2024 · similarity 0.88)
- Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion (CVPR 2025 · similarity 0.88)
- Improving Depth Completion via Depth Feature Upsampling (CVPR 2024 · similarity 0.86)
- Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data (CVPR 2024 · similarity 0.86)
- Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (ICLR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
