Research map / 3D vision / 3D generation
Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes From a Single Image
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| jointly train layout, object detection, and mesh reconstruction with cooperative and global losses (ablation) | Total3DUnderstanding · SUN RGB-D | 3D object detection mAP: 20.19 -> 26.38 | Helped |
| jointly train layout, object detection, and mesh reconstruction with cooperative and global losses (ablation) | Total3DUnderstanding · SUN RGB-D | layout IoU: 57.63 -> 58.87 | Helped |
| add relational features to ODN (ablation) | Total3DUnderstanding · SUN RGB-D | 3D object detection mAP: 20.19 -> 23.32 | Helped |
| add cooperative loss (ablation) | Total3DUnderstanding · SUN RGB-D | layout IoU: 57.63 -> 58.21 | Helped |
| add global scene geometry loss (ablation) | Total3DUnderstanding · SUN RGB-D | 3D object detection mAP: 20.19 -> 24.59 | Helped |
| use cooperative and global losses together (ablation) | Total3DUnderstanding · SUN RGB-D | 3D object detection mAP: 24.59 -> 25.62 | Helped |
| cut mesh edges rather than remove faces (ablation) | Total3DUnderstanding mesh generation · Pix3D | mean mesh Chamfer distance (10^-3): 8.84 -> 8.36 | Helped |
| use local density rather than a distance threshold for topology modification (ablation) | Total3DUnderstanding mesh generation · Pix3D | mean mesh Chamfer distance (10^-3): 8.75 -> 8.36 | Helped |
| fine-tune mesh generation on SUN RGB-D partial point clouds (ablation) | Total3DUnderstanding mesh generation · Pix3D | single-object mesh reconstruction | No clear effect |
Closest papers by meaning
- Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping (NeurIPS 2025 · similarity 0.88)
- Behind the Veil: Enhanced Indoor 3D Scene Reconstruction with Occluded Surfaces Completion (CVPR 2024 · similarity 0.87)
- HouseLayout3D: A Benchmark and Training-free Baseline for 3D Layout Estimation in the Wild (NeurIPS 2025 · similarity 0.87)
- Hierarchically-Structured Open-Vocabulary Indoor Scene Synthesis with Pre-trained Large Language Model (AAAI 2025 · similarity 0.87)
- Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning (CVPR 2024 · similarity 0.87)
- SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes (CVPR 2024 · 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.