Research map / 3D vision / Gaussian splatting
GGRt: Towards Generalizable 3D Gaussians without Pose Priors in Real-Time
Hao Li, Yuanyuan Gao, Dingwen Zhang, Chenming Wu, YALUN DAI, Chen Zhao, Haocheng Feng, Errui Ding, Jingdong Wang, Junwei Han
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 Gaussians cache (ablation) | GGRt · Waymo 019 | inference time: 1.02s/iter -> 0.13s/iter | Improved |
| add Gaussians cache (ablation) | GGRt · Waymo 019 | PSNR: 32.34 -> 32.34 | No clear effect |
| add deferred back-propagation to enable 5 views at higher resolution (ablation) | GGRt · LLFF room | PSNR: 26.00 -> 29.02 (generalized) | Improved |
| train with cropped images instead of deferred back-propagation (ablation) | GGRt · high-resolution rendering | PSNR: 28.25 -> 24.22 | Hurt |
| add local self-attention in deferred back-propagation (ablation) | GGRt · training PSNR curve | training PSNR | Improved |
| use joint training of IPO-Net with G-3DG instead of DBARF pose estimation | pose-free NVS · LLFF rotation error (Trex) | rotation error (degrees): 126.93 -> 3.449 | Improved |
| use GGRt instead of DBARF | pose-free NVS · Waymo scene 69 | PSNR: 21.97 -> 32.10 | Improved |
| use GGRt (pose-free) instead of pose-based IBRNet on Waymo 126 | NVS · Waymo scene 126 | PSNR: 36.00 -> 34.15 | Hurt |
| rotation error on LLFF leaves with GGRt versus DBARF | IPO-Net · LLFF leaves | rotation error (degrees): 13.927 -> 16.964 | Hurt |
Later papers that compared with this method
1 later accepted paper reports GGRT as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- UV-RGS: Relightable 3D Gaussian Splatting from Unposed Views Under Varied Illuminations (AAAI 2026 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- DBARF — DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields (CVPR 2023) · better on 2 of 2 shared results
- FlowCAM — FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow (NeurIPS 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
- COLMAP-Free 3D Gaussian Splatting (CVPR 2024 · similarity 0.90)
- No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images (ICLR 2025 · similarity 0.90)
- SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting (CVPR 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)
- PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting for Novel View Synthesis (ICML 2025 · 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.
