Research map / 3D vision / Gaussian splatting
Cross-temporal 3D Gaussian Splatting for Sparse-view Guided Scene Update
Zeyuan An, Yanghang Xiao, Zhiying Leng, Frederick W. B. Li, Xiaohui Liang
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 cross-temporal camera alignment (coarse registration) (ablation) | Cross-Temporal 3DGS · Cross-temporal dataset | PSNR: 23.67 -> 23.89 | Improved |
| add ICP refinement after coarse alignment (ablation) | Cross-Temporal 3DGS · Cross-temporal dataset | PSNR: 21.84 -> 23.89 | Improved |
| add interference-based confidence estimation instead of directly fine-tuning G0 (ablation) | Cross-Temporal 3DGS · Cross-temporal dataset | PSNR: 19.38 -> 23.89 | Improved |
| add progressive confidence refinement over fixed initial maps (ablation) | Cross-Temporal 3DGS · Cross-temporal dataset | LPIPS: 0.291 -> 0.2394 | Improved |
| add progressive refinement, training time cost (ablation) | Cross-Temporal 3DGS · Cross-temporal dataset | training time (s): 271.25 -> 310.00 | Hurt |
| use cross-temporal priors instead of direct sparse-view 3DGS | 3DGS · Cross-temporal dataset | PSNR: 15.87 -> 23.89 | Improved |
| use cross-temporal priors instead of direct sparse-view 3DGS | 3DGS · Cross-temporal dataset | training time (s): 160.55 -> 310.00 | Hurt |
| increase sparse views from 4 to 8 (uniform) (ablation) | Cross-Temporal 3DGS · Cross-temporal dataset | PSNR: 23.32 -> 23.89 | Improved |
| use uniform instead of concentrated view layout (8 views) (ablation) | Cross-Temporal 3DGS · Cross-temporal dataset | LPIPS: 0.263 -> 0.239 | Improved |
Closest papers by meaning
- KeyGS: A Keyframe-Centric Gaussian Splatting Method for Monocular Image Sequences (AAAI 2025 · similarity 0.89)
- Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.89)
- Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputs (CVPR 2025 · similarity 0.89)
- DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos (NeurIPS 2025 · similarity 0.89)
- Graph-Guided Scene Reconstruction from Images with 3D Gaussian Splatting (ICLR 2025 · similarity 0.89)
- Metropolis-Hastings Sampling for 3D Gaussian Reconstruction (NeurIPS 2025 · similarity 0.89)
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.
