Research map / 3D vision / Depth and stereo
Holo360D: A Large-Scale Real-World Dataset with Continuous Trajectories for Advancing Panoramic 3D Reconstruction and Beyond
Jing OU, Zidong Cao, Yinrui Ren, Zhuoxiao Li, Jinjing Zhu, Tongyan Hua, Shuai Zhang, Hui Xiong, Wufan 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 |
|---|---|---|---|
| fine-tune on Holo360D | pi3 · Holo360D test, indoor | ATE: 0.093 -> 0.014 | Improved |
| fine-tune on Holo360D | VGGT · Holo360D test, indoor | ATE: 0.231 -> 0.084 | Improved |
| fine-tune on Holo360D | FLARE · Holo360D test, indoor | AUC@30: 0.256 -> 0.515 | Improved |
| split panoramas into perspective views instead of feeding full panoramas (ablation) | pi3 fine-tuning · Holo360D test, outdoor | point map Acc.: 0.718 -> 0.194 | Improved |
| split panoramas into perspective views instead of full panoramas (ablation) | pi3 fine-tuning · Holo360D test, indoor | ATE: 0.018 -> 0.014 | Improved |
| use 8 horizontal views instead of adding up/down views (10 views) (ablation) | pi3 fine-tuning · Holo360D test, outdoor | RPE_r: 0.623 -> 0.208 | Improved |
| supervise with mesh depth instead of point depth (ablation) | pi3 fine-tuning · Holo360D test, indoor | ATE: 0.054 -> 0.014 | Improved |
| add point-depth fine-tuning after mesh-depth training (ablation) | pi3 fine-tuning · Holo360D test, outdoor | point map Acc.: 0.194 -> 0.189 | Improved |
| fine-tune on Holo360D instead of Matterport3D | pi3 · Holo360D test, indoor | ATE: 0.428 -> 0.014 | Improved |
Closest papers by meaning
- Unified Panoramic Geometry Estimation via Multi-View Foundation Models (NeurIPS 2026 · similarity 0.87)
- Splatter-360: Generalizable 360 Gaussian Splatting for Wide-baseline Panoramic Images (CVPR 2025 · similarity 0.87)
- DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images (NeurIPS 2026 · similarity 0.86)
- PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation (CVPR 2025 · similarity 0.85)
- Scene4U: Hierarchical Layered 3D Scene Reconstruction from Single Panoramic Image for Your Immerse Exploration (CVPR 2025 · similarity 0.84)
- PanoWorld: Geometry-Consistent Panoramic Video World Modeling (NeurIPS 2026 · 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.
