Research map / 3D vision / 3D generation
ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes
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 |
|---|---|---|---|
| train the 3D classifier on ScanNet instead of SceneNN | 3D Network-in-Network · SceneNN | average instance accuracy: 69.8 -> 78.8 | Helped |
| train the 3D classifier on ScanNet instead of NYU | 3D Network-in-Network · ScanNet | average instance accuracy: 53.2 -> 74.9 | Helped |
| add partial ShapeNet training data to ScanNet training | 3D Network-in-Network · ScanNet | average instance accuracy: 74.9 -> 76.6 | Helped |
| use ScanNet and NYU training data with the proposed geometry-only network | NYU2 semantic labeling · NYU2 | average pixel classification accuracy: 59.6 -> 60.7 | Helped |
| train the retrieval embedding jointly on ScanNet and ShapeNet | 3D Network-in-Network retrieval embedding · ScanNet objects queried against ShapeNetCore | Top 1 NN average instance accuracy: 10.4% -> 77.5% | Helped |
Closest papers by meaning
- MultiScan: Scalable RGBD scanning for 3D environments with articulated objects (NeurIPS 2022 · similarity 0.90)
- Learning 3D Semantic Scene Graphs From 3D Indoor Reconstructions (CVPR 2020 · similarity 0.89)
- 3D-to-2D Distillation for Indoor Scene Parsing (CVPR 2021 · similarity 0.89)
- RevealNet: Seeing Behind Objects in RGB-D Scans (CVPR 2020 · similarity 0.88)
- ImageNet3D: Towards General-Purpose Object-Level 3D Understanding (NeurIPS 2024 · similarity 0.87)
- Large Spatial Model: End-to-end Unposed Images to Semantic 3D (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.