Research map / Point clouds / Point cloud classification
DReg-NeRF: Deep Registration for Neural Radiance Fields
Yu Chen, Gim Hee Lee
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 |
|---|---|---|---|
| supervise with surface fields instead of density fields (ablation) | DReg-NeRF · Objaverse NeRF registration (44 test objects) | relative rotation error (deg): 86.22 -> 9.67 | Improved |
| add surface field loss (ablation) | DReg-NeRF · Objaverse NeRF registration (44 test objects) | relative rotation error (deg): 101.17 -> 9.67 | Improved |
| add confidence loss (ablation) | DReg-NeRF · Objaverse NeRF registration (44 test objects) | relative rotation error (deg): 71.84 -> 9.67 | Improved |
| add surface field loss (ablation) | DReg-NeRF · Objaverse NeRF registration (44 test objects) | relative translation error (x1e2): 20.35 -> 3.85 | Improved |
| use learned NeRF registration instead of FGR on voxel point clouds | NeRF block registration · Objaverse NeRF registration (44 test objects) | relative rotation error (deg): 61.59 -> 9.67 | Improved |
| use point cloud registration model REGTR pre-trained on 3DMatch without retraining | NeRF block registration · Objaverse NeRF registration (44 test objects) | relative rotation error (deg): 61.59 (FGR) -> 113.78 (REGTR) | Hurt |
| use density-field supervision (Ours_df) on individual objects (ablation) | DReg-NeRF · Objaverse NeRF registration (44 test objects) | relative rotation error (deg): 86.22 vs 9.67 | Hurt |
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.
- REGTR — REGTR: End-to-End Point Cloud Correspondences With Transformers (CVPR 2022) · better on 2 of 2 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
- VF-NeRF: Viewshed Fields for Rigid NeRF Registration (ECCV 2024 · similarity 0.90)
- D-NeRF: Neural Radiance Fields for Dynamic Scenes (CVPR 2021 · similarity 0.90)
- Depth-Supervised NeRF: Fewer Views and Faster Training for Free (CVPR 2022 · similarity 0.89)
- Mask-Based Modeling for Neural Radiance Fields (ICLR 2024 · similarity 0.88)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.88)
- Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset Updates (CVPR 2024 · 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.
