Research map / 3D vision / Gaussian splatting
Splat-SAP: Feed-Forward Gaussian Splatting for Human-Centered Scene with Scale-Aware Point Map Reconstruction
Boyao Zhou, Shunyuan Zheng, Zhanfeng Liao, Zihan Ma, Hanzhang Tu, Boning Liu, Yebin Liu
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 iterative pixel-wise translation learning (ablation) | Splat-SAP scale-aware point map · Geometry (SfM GT point set) | Chamfer GT->Pred: 0.046 -> 0.027 | Improved |
| add iterative pixel-wise translation learning (ablation) | Splat-SAP scale-aware point map · Geometry (SfM GT point set) | Chamfer Pred->GT: 0.191 -> 0.172 | Improved |
| add stage-2 3D refinement module (ablation) | Splat-SAP · Qualitative (no numbers) | rendering holes at boundaries | Improved |
| Splat-SAP vs MVSplat on mobile-phone data | MVSplat · Mobile dataset (rendering) | PSNR: 26.545 vs 25.721 | No clear effect |
| Splat-SAP vs MVSGaussian on camera data LPIPS | MVSGaussian · Camera dataset (rendering) | LPIPS: 0.069 -> 0.079 | Hurt |
| Splat-SAP vs best baseline on camera data | ENeRF/MVSGaussian · Camera dataset (rendering) | PSNR: 29.326 -> 32.220 | Improved |
| Splat-SAP vs best baseline on GoPro data | MVSplat · GoPro dataset (rendering) | PSNR: 29.942 -> 31.640 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- MVSplat — MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images (ECCV 2024) · better on 4 of 5 shared results
- VGGT — VGGT: Visual Geometry Grounded Transformer (CVPR 2025) · better on 2 of 2 shared results
- DUSt3R — DUSt3R: Geometric 3D Vision Made Easy (CVPR 2024) · 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
- FreeSplat: Generalizable 3D Gaussian Splatting Towards Free View Synthesis of Indoor Scenes (NeurIPS 2024 · similarity 0.91)
- COLMAP-Free 3D Gaussian Splatting (CVPR 2024 · similarity 0.91)
- FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training (NeurIPS 2024 · similarity 0.90)
- Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis (NeurIPS 2024 · similarity 0.90)
- Generative Sparse-View Gaussian Splatting (CVPR 2025 · similarity 0.89)
- Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting (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.
