Research map / 3D vision / Depth and stereo
IM360: Large-scale Indoor Mapping with 360 Cameras
Dongki Jung, Jaehoon Choi, Yonghan Lee, Dinesh Manocha
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 texture optimization on diffuse texture (ablation) | TexRecon texture mapping · Matterport3D rendering | PSNR: 15.9 -> 18.6 | Improved |
| add specular component with small MLP shader (ablation) | IM360 diffuse-only · Matterport3D rendering | PSNR: 18.6 -> 19.4 | Improved |
| add specular component (ablation) | IM360 diffuse-only · Matterport3D rendering | SSIM: 0.63 -> 0.67 | Improved |
| add specular component (ablation) | IM360 diffuse-only · Matterport3D rendering | LPIPS: 0.39 -> 0.37 | Improved |
| full IM360 mesh texturing instead of TexRecon | TexRecon · Matterport3D rendering | PSNR: 15.9 -> 19.4 | Improved |
| mesh texture vs 3DGS rendering | 3DGS · Matterport3D rendering | PSNR: 13.4 -> 19.4 | Improved |
| spherical SfM with dense matching instead of cubemap DKM COLMAP | DKM COLMAP · Matterport3D 2t7WUuJeko7 | registered images: 22 / 37 -> 37 / 37 | Improved |
| spherical SfM with dense matching | DKM COLMAP · Stanford2D3D area 4 | AUC@10: 4.40 -> 71.29 | Improved |
| spherical SfM | SPSG COLMAP · Matterport3D YVUC4YcDtcY | AUC@10: 95.26 -> 91.71 | Hurt |
| spherical SfM | DKM COLMAP · Matterport3D pLe4wQe7qrG | AUC@10: 92.78 -> 92.18 | No clear effect |
| initialize two-view poses with Solarte et al. method (ablation) | IM360 SfM · Matterport3D | registration | Improved |
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.
- ZipNeRF — Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields (ICCV 2023) · better on 3 of 3 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
- 360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device Queries (CVPR 2024 · similarity 0.87)
- Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping (NeurIPS 2025 · similarity 0.86)
- SCRREAM : SCan, Register, REnder And Map: A Framework for Annotating Accurate and Dense 3D Indoor Scenes with a Benchmark (NeurIPS 2024 · similarity 0.86)
- Shading Meets Motion: Self-supervised Indoor 3D Reconstruction Via Simultaneous Shape-from-Shading and Structure-from-Motion (CVPR 2025 · similarity 0.84)
- RoomPainter: View-Integrated Diffusion for Consistent Indoor Scene Texturing (CVPR 2025 · similarity 0.84)
- Large Spatial Model: End-to-end Unposed Images to Semantic 3D (NeurIPS 2024 · 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.
