Research map / 3D vision / Depth and stereo
Multi-modal Masked Pre-training for Monocular Panoramic Depth Completion
Zhiqiang Yan, Xiang Li, Kun Wang, Zhenyu Zhang, Jun Li, Jian Yang
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 |
|---|---|---|---|
| add shared random masked pre-training (mask size 16, ratio 0.75) (ablation) | GuideNet · Stanford2D3D | RMSE (mm): 196.7 -> 167.6 | Improved |
| use shared mask on RGB-D instead of independent masks (ablation) | M3PT · Stanford2D3D | RMSE (mm): 182.2 -> 167.6 | Improved |
| mask RGB and depth together instead of RGB only (ablation) | M3PT · Stanford2D3D | RMSE (mm): 194.0 -> 167.6 | Improved |
| mask RGB and depth together instead of depth only (ablation) | M3PT · Stanford2D3D | RMSE (mm): 186.1 -> 167.6 | Improved |
| increase mask size from 16 to 32 (ablation) | M3PT · Stanford2D3D | RMSE (mm): 167.6 -> 169.9 | Hurt |
| vary mask size 4, 8, 16 with shared mask (ablation) | M3PT · Stanford2D3D | RMSE (mm): 166.8, 168.9, 167.6 | No clear effect |
| increase mask ratio from 0.15 to 0.75 (size 16) (ablation) | M3PT · Stanford2D3D | RMSE (mm): 173.5 -> 167.6 | Improved |
| extend training without pre-training from 100 to 400 epochs (ablation) | GuideNet · Stanford2D3D | RMSE (mm): 196.7 -> 196.3 | No clear effect |
| pre-train on all three datasets instead of only own data (ablation) | M3PT · Stanford2D3D | RMSE (mm): 167.6 -> 149.0 | Improved |
| pre-train on all three datasets instead of only own data (ablation) | M3PT · Matterport3D | RMSE (mm): 146.2 -> 138.9 | Improved |
| add M3PT pre-training | S2D · KITTI validation | RMSE (mm): 858.02 -> 844.16 | Improved |
| add M3PT pre-training | GuideNet · KITTI validation | RMSE (mm): 777.78 -> 761.57 | Improved |
Closest papers by meaning
- CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion (NeurIPS 2022 · similarity 0.87)
- Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation (CVPR 2026 · similarity 0.87)
- Distortion and Uncertainty Aware Loss for Panoramic Depth Completion (ICML 2023 · similarity 0.87)
- Distilling Monocular Foundation Model for Fine-grained Depth Completion (CVPR 2025 · similarity 0.87)
- Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior (AAAI 2025 · similarity 0.86)
- PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation (CVPR 2025 · similarity 0.85)
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.
