Research map / 3D vision / Depth and stereo
Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes
Xi Li, Linyuan Li, Yan Wu, Tong Rao, Kai Zhang, Xinchen Hui, Cihui Pan
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 reference view learning (ablation) | Argus · Realsee3D Synthetic ablation | ATE: 0.060 -> 0.027 | Improved |
| add reference view learning (ablation) | Argus · Realsee3D Synthetic ablation | AbsRel: 0.037 -> 0.035 | Improved |
| add geometric joint loss (ablation) | Argus · Realsee3D Synthetic ablation | AbsRel: 0.047 -> 0.035 | Improved |
| add geometric joint loss (ablation) | Argus · Realsee3D Synthetic ablation | ATE: 0.049 -> 0.027 | Improved |
| add camera-coordinate point map loss (ablation) | Argus · Realsee3D Synthetic ablation | AbsRel: 0.055 -> 0.035 | Improved |
| add reference-coordinate point map loss (ablation) | Argus · Realsee3D Synthetic ablation | AbsRel: 0.045 -> 0.035 | Improved |
| add all three point map losses (ablation) | Argus · Realsee3D Synthetic ablation | AbsRel: 0.075 -> 0.035 | Improved |
| add all three point map losses (ablation) | Argus · Realsee3D Synthetic ablation | RMSE: 0.169 -> 0.139 | Improved |
| add reference view learning (ablation) | Argus · Realsee3D Real ATE, fewer than 20 views | ATE: 0.092 -> 0.082 | Improved |
| add reference view learning (ablation) | Argus · Realsee3D Real ATE, 20 to 30 views | ATE: 0.138 -> 0.087 | Improved |
| add reference view learning (ablation) | Argus · Realsee3D Real ATE, more than 30 views | ATE: 0.233 -> 0.152 | Improved |
| train on real plus synthetic instead of real only (ablation) | Argus · Realsee3D Real | AbsRel: 0.047 -> 0.050 | Hurt |
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.
- VGGT360 — VGGT: Visual Geometry Grounded Transformer (CVPR 2025) · better on 5 of 5 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
- CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage (NeurIPS 2026 · similarity 0.88)
- Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation (CVPR 2026 · similarity 0.87)
- SO(3)-Equivariant ViT-Adapter for Data-Efficient Zero-Shot Sim-to-Real Indoor Panoramic Depth Estimation (CVPR 2026 · similarity 0.87)
- Unified Panoramic Geometry Estimation via Multi-View Foundation Models (NeurIPS 2026 · similarity 0.86)
- DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images (NeurIPS 2026 · similarity 0.85)
- UniK3D: Universal Camera Monocular 3D Estimation (CVPR 2025 · similarity 0.84)
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.
