Research map / 3D vision / 3D generation
ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes
Chandan Yeshwanth, Yueh-Cheng Liu, Matthias Nießner, Angela Dai
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 |
|---|---|---|---|
| train NVS on iPhone video instead of DSLR images | Nerfacto · ScanNet++ NVS | PSNR: 25.02 -> 17.70 | Hurt |
| train NVS on iPhone video instead of DSLR images | Instant-NGP · ScanNet++ NVS | PSNR: 24.67 -> 15.18 | Hurt |
| apply a cross-scene pix2pix refiner to Nerfacto renderings | Nerfacto · ScanNet++ NVS (DSLR) | PSNR: 25.02 -> 25.42 | Improved |
| apply a cross-scene pix2pix refiner to Nerfacto renderings | Nerfacto · ScanNet++ NVS (DSLR) | LPIPS: 0.180 -> 0.156 | Improved |
| use Nerfacto (combined state-of-the-art components) instead of vanilla NeRF | NVS on ScanNet++ · ScanNet++ NVS (DSLR) | PSNR: 24.11 -> 25.02 | Improved |
| use KPConv instead of PointNet for 3D semantic segmentation | ScanNet++ semantic segmentation · ScanNet++ semantic segmentation | mIoU: 0.07 -> 0.30 | Improved |
| use SoftGroup instead of PointGroup for instance segmentation | ScanNet++ instance segmentation · ScanNet++ instance segmentation | AP50: 0.148 -> 0.237 | Improved |
Closest papers by meaning
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes (CVPR 2017 · similarity 0.93)
- MultiScan: Scalable RGBD scanning for 3D environments with articulated objects (NeurIPS 2022 · similarity 0.89)
- SceneNet RGB-D: Can 5M Synthetic Images Beat Generic ImageNet Pre-Training on Indoor Segmentation? (ICCV 2017 · similarity 0.89)
- 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation (ECCV 2018 · similarity 0.89)
- SSR-2D: Semantic 3D Scene Reconstruction From 2D Images (TPAMI 2024 · similarity 0.88)
- 3D-to-2D Distillation for Indoor Scene Parsing (CVPR 2021 · similarity 0.88)
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.
