Research map / 3D vision / Depth and stereo
VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimation
Jiayi Yuan, Haobo Jiang, De Wen Soh, Na Zhao
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 structure-saliency prior Mg to VGGT attention (ablation) | VGGT · Stanford2D3D | Abs Rel: 0.080 -> 0.075 | Improved |
| add edge-band prior E (ablation) | VGGT with Mg · Stanford2D3D | Abs Rel: 0.075 -> 0.073 | Improved |
| add edge-band prior E (ablation) | VGGT with Mg · Stanford2D3D | RMSE: 0.343 -> 0.346 | No clear effect |
| add validity mask 1valid (ablation) | VGGT with Mg and E · Stanford2D3D | Abs Rel: 0.073 -> 0.072 | Improved |
| add correlation-weighted 3D correction with all three cues (ablation) | VGGT · Stanford2D3D | Abs Rel: 0.080 -> 0.071 | Improved |
| use any single correlation cue (sharpness, locality or symmetry) (ablation) | VGGT · Stanford2D3D | Abs Rel: 0.080 -> 0.073 to 0.074 | Improved |
| use adaptive projection (NB=8, K=2) instead of uniform views (ablation) | VGGT-360 · Stanford2D3D | accuracy vs runtime | Improved |
| apply VGGT-360 to panoramas instead of view-independent 360MD | VGGT-like models · Matterport3D | Abs Rel: 0.264 -> 0.083 | Improved |
| swap VGGT backbone for Fastvggt or pi3 | VGGT-360 · Replica360-2K | Abs Rel: 0.075 -> 0.069 (Fastvggt), 0.070 (pi3) | Improved |
Closest papers by meaning
- DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images (NeurIPS 2026 · similarity 0.90)
- Unified Panoramic Geometry Estimation via Multi-View Foundation Models (NeurIPS 2026 · similarity 0.90)
- Splatter-360: Generalizable 360 Gaussian Splatting for Wide-baseline Panoramic Images (CVPR 2025 · similarity 0.89)
- VGGT: Visual Geometry Grounded Transformer (CVPR 2025 · similarity 0.88)
- PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation (CVPR 2025 · similarity 0.87)
- TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention (NeurIPS 2026 · 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.
