Research map / 3D vision / Depth and stereo
OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramas
Nikolaos Zioulis, Antonis Karakottas, Dimitrios Zarpalas, Petros Daras
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 RectNet (360-aware, larger receptive field) instead of UResNet | depth network · 360D test set | Abs Rel: 0.0835 -> 0.0702 | Improved |
| use RectNet instead of UResNet | depth network · SceneNet (trained on 360D) | Abs Rel: 0.1218 -> 0.1077 | Improved |
| use RectNet instead of UResNet | depth network · Stanford (S2R) | Abs Rel: 0.1226 -> 0.0824 | Improved |
| use RectNet instead of UResNet | depth network · SceneNet (S2R) | Abs Rel: 0.1448 -> 0.1079 | Improved |
| use RectNet instead of UResNet | depth network · 360D test set | delta < 1.25: 0.9319 -> 0.9574 | Improved |
| use RectNet instead of UResNet on cube faces | depth network · 360D test set, per cube face | Abs Rel: 0.0097 -> 0.008 | Improved |
| run monocular baselines on cubemap faces instead of equirectangular input | Laina et al. · 360D test set | Abs Rel: 0.3181 -> 0.1423 | Improved |
| run monocular baselines on cubemap faces instead of equirectangular input | Godard et al. · 360D test set | Abs Rel: 0.4747 -> 0.2552 | Improved |
| run monocular baselines on cubemap faces instead of equirectangular input | Liu et al. · 360D test set | Abs Rel: 0.4202 -> 0.1869 | Improved |
| train directly on 360 data (RectNet) instead of using perspective-trained models on cubemap | RectNet vs Laina et al. · 360D test set | Abs Rel: 0.1423 -> 0.0702 | Improved |
Closest papers by meaning
- HELVIPAD: A Real-World Dataset for Omnidirectional Stereo Depth Estimation (CVPR 2025 · similarity 0.89)
- DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images (NeurIPS 2026 · similarity 0.89)
- Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation (NeurIPS 2024 · similarity 0.88)
- GeoDepth: From Point-to-Depth to Plane-to-Depth Modeling for Self-Supervised Monocular Depth Estimation (CVPR 2025 · similarity 0.88)
- RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimization (NeurIPS 2025 · similarity 0.87)
- Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data (CVPR 2024 · similarity 0.87)
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.
