Research map / 3D vision / 3D generation
Diorama: Unleashing Zero-shot Single-view 3D Indoor Scene Modeling
Qirui Wu, Denys Iliash, Daniel Ritchie, Manolis Savva, Angel X. Chang
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 |
|---|---|---|---|
| use PlainRecon with Metric3DV2 depth instead of DepthAnythingV2 (ablation) | PlainRecon · SSDB architecture reconstruction | IoU: 47.8 -> 58.6 | Improved |
| PlainRecon instead of RaC and ACDC (same DAv2 depth) | architecture reconstruction · SSDB architecture reconstruction | IoU: 46.8 -> 47.8 | Improved |
| PlainRecon instead of RaC | architecture reconstruction · SSDB architecture reconstruction | RMSE: 0.67 -> 1.26 | Hurt |
| add orientation term to scene optimization (ablation) | scene optimization · SSDB scene optimization ablation | orientation accuracy: 0.19 -> 0.98 | Improved |
| add placement term to scene optimization (ablation) | scene optimization · SSDB scene optimization ablation | overall scene structure: 0.01 -> 0.91 | Improved |
| add placement term to scene optimization (ablation) | scene optimization · SSDB scene optimization ablation | Collision: 5.17 -> 8.08 | Hurt |
| add space term (ablation) | scene optimization · SSDB scene optimization ablation | Collision: 8.08 -> 6.08 | Improved |
| add refinement term (ablation) | scene optimization · SSDB scene optimization ablation | Collision: 6.08 -> 3.78 | Improved |
| stage-wise instead of all-in-one optimization (ablation) | scene optimization · SSDB scene optimization ablation | overall scene structure: 0.16 -> 0.93 | Improved |
| stage-wise instead of all-in-one optimization (ablation) | scene optimization · SSDB scene optimization ablation | Collision: 12.80 -> 3.78 | Improved |
| use ground-truth scene graph (ablation) | scene optimization · SSDB scene optimization ablation | Collision: 3.78 -> 3.12 | Improved |
| use both text and visual modalities for retrieval vs visual only (ablation) | DuoduoCLIP retrieval · SSDB shape retrieval (SSDB shapes, Household) | Chamfer distance: 6.4 -> 5.5 | 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.
- GigaPose — GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence (CVPR 2024) · better on 1 of 1 shared result
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
- Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling (ECCV 2020 · similarity 0.88)
- CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage (NeurIPS 2026 · similarity 0.88)
- Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes From a Single Image (CVPR 2020 · similarity 0.88)
- ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image (CVPR 2024 · similarity 0.87)
- SparseGNV: Generating Novel Views of Indoor Scenes with Sparse RGB-D Images (AAAI 2024 · similarity 0.86)
- DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features (NeurIPS 2024 · similarity 0.86)
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.
