Research map / 3D vision / Gaussian splatting
RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registration
Chong Cheng, Yu Hu, Sicheng Yu, Beizhen Zhao, Zijian Wang, Hao Wang
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 |
|---|---|---|---|
| add photometric loss to joint registration (ablation) | RegGS · RE10K, 16 views | PSNR: 16.06 -> 23.09 | Improved |
| add depth-consistency loss (ablation) | RegGS · RE10K, 16 views | PSNR: 20.97 -> 23.09 | Improved |
| add MW2 loss (ablation) | RegGS · RE10K, 16 views | ATE: 1.151 -> 0.098 | Improved |
| add MW2 loss (ablation) | RegGS · RE10K, 16 views | MW2 distance: 67.7 -> 56.5 | Improved |
| add photometric loss (ablation) | RegGS · RE10K, 16 views | ATE: 1.184 -> 0.098 | Improved |
| add depth-consistency loss (ablation) | RegGS · RE10K, 16 views | ATE: 0.160 -> 0.098 | Improved |
| add joint 3DGS registration module (ablation) | RegGS · RE10K, 16 views | PSNR: 11.41 -> 23.09 | Improved |
| add joint 3DGS registration module (ablation) | RegGS · RE10K, 16 views | ATE: 1.164 -> 0.098 | Improved |
| use RegGS instead of MASt3R* with 2 views | RegGS · RE10K, 2 views | PSNR: 16.036 -> 24.272 | Improved |
| use RegGS instead of MASt3R* with 32 views | RegGS · RE10K, 32 views | PSNR: 28.309 -> 28.332 | No clear effect |
| use RegGS instead of CF3DGS for pose | RegGS · RE10K, 16 views | ATE: 0.254 -> 0.041 | Improved |
| use RegGS instead of NoPoSplat with 2 views | RegGS · RE10K, 2 views | LPIPS: 0.111 -> 0.174 | 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.
- NoPeNerf — NoPe-NeRF: Optimising Neural Radiance Field With No Pose Prior (CVPR 2023) · 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
- Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views (CVPR 2025 · similarity 0.91)
- TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers (AAAI 2025 · similarity 0.90)
- KeyGS: A Keyframe-Centric Gaussian Splatting Method for Monocular Image Sequences (AAAI 2025 · similarity 0.90)
- SfM-Free 3D Gaussian Splatting via Hierarchical Training (CVPR 2025 · similarity 0.90)
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
- DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus (NeurIPS 2024 · similarity 0.90)
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.
