Research map / 3D vision / Depth and stereo
360MonoDepth: High-Resolution 360deg Monocular Depth Estimation
Manuel Rey-Area, Mingze Yuan, Christian Richardt
Check 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 |
|---|---|---|---|
| apply 360MonoDepth with MiDaS v2 multi-scale alignment on unseen Replica360-2K | 360MonoDepth · Replica360-2K | AbsRel: 0.182 -> 0.167 | Improved |
| add tangent-image alignment instead of no alignment (ablation) | 360MonoDepth with MiDaS v3 · Matterport3D test | AbsRel: 0.259 -> 0.208 | Improved |
| use multi-scale alignment rather than a 2x2 single-scale grid (ablation) | 360MonoDepth with MiDaS v3 · Matterport3D test | AbsRel: 0.210 -> 0.208 | Improved |
| use multi-scale alignment rather than a 4x3 single-scale grid (ablation) | 360MonoDepth with MiDaS v3 · Matterport3D test | AbsRel: 0.210 -> 0.208 | Improved |
| use multi-scale alignment rather than an 8x7 single-scale grid (ablation) | 360MonoDepth with MiDaS v3 · Matterport3D test | AbsRel: 0.210 -> 0.208 | Improved |
| use multi-scale alignment rather than a 16x14 single-scale grid (ablation) | 360MonoDepth with MiDaS v3 · Matterport3D test | AbsRel: 0.231 -> 0.208 | Improved |
| replace nearest-neighbour blending with Poisson blending (ablation) | 360MonoDepth with MiDaS v2 · Matterport3D test | AbsRel: 0.226 -> 0.224 | Improved |
| replace mean blending with Poisson blending (ablation) | 360MonoDepth with MiDaS v2 · Matterport3D test | AbsRel: 0.230 -> 0.224 | Improved |
| replace frustum blending with Poisson blending (ablation) | 360MonoDepth with MiDaS v2 · Matterport3D test | AbsRel: 0.229 -> 0.224 | Improved |
Closest papers by meaning
- Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (ICLR 2025 · similarity 0.89)
- Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation (NeurIPS 2024 · similarity 0.88)
- DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images (NeurIPS 2026 · similarity 0.88)
- GeoDepth: From Point-to-Depth to Plane-to-Depth Modeling for Self-Supervised Monocular Depth Estimation (CVPR 2025 · similarity 0.88)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · similarity 0.88)
- RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimization (NeurIPS 2025 · 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.
