Research map / 3D vision / Gaussian splatting
FreeSplat++: Generalizable 3D Gaussian Splatting for Efficient Indoor Scene Reconstruction
Yunsong Wang, Tianxin Huang, Hanlin 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 |
|---|---|---|---|
| add cost volume (ablation) | FreeSplat++ · ScanNet whole scene | iPSNR: 18.90 -> 23.29 | Improved |
| add cost volume (ablation) | FreeSplat++ · ScanNet++ whole scene | iPSNR: 18.74 -> 22.63 | Improved |
| add pixel-wise triplet fusion (ablation) | FreeSplat++ · ScanNet whole scene | iPSNR: 22.11 -> 23.29 | Improved |
| add pixel-wise triplet fusion (ablation) | FreeSplat++ · ScanNet++ whole scene | iPSNR: 18.88 -> 22.63 | Improved |
| add floater removal (ablation) | FreeSplat++ · ScanNet++ whole scene | iPSNR: 20.02 -> 22.63 | Improved |
| add floater removal (ablation) | FreeSplat++ · ScanNet whole scene | iPSNR: 22.88 -> 23.29 | Improved |
| add broader fusion (ablation) | FreeSplat++ · ScanNet++ whole scene | iPSNR: 20.74 -> 22.63 | Improved |
| add free view training (ablation) | FreeSplat++ · ScanNet whole scene | iPSNR: 22.90 -> 23.29 | Improved |
| add free view training (ablation) | FreeSplat++ · ScanNet++ whole scene | iPSNR: 22.35 -> 22.63 | Improved |
| add lower-resolution unprojection (ablation) | FreeSplat++ · ScanNet whole scene | Gaussians (M): 6.27 -> 1.46 | Improved |
| add lower-resolution unprojection (ablation) | FreeSplat++ · ScanNet++ whole scene | iPSNR: 22.70 -> 22.63 | No clear effect |
| add depth supervision in training (ablation) | FreeSplat++ · ScanNet | iPSNR: 23.29 -> 23.10 | Hurt |
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.
- MVSplat — MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images (ECCV 2024) · better on 7 of 7 shared results
- pixelSplat* — pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction (CVPR 2024) · 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
- FreeSplat: Generalizable 3D Gaussian Splatting Towards Free View Synthesis of Indoor Scenes (NeurIPS 2024 · similarity 0.94)
- IndoorGS: Geometric Cues Guided Gaussian Splatting for Indoor Scene Reconstruction (CVPR 2025 · similarity 0.92)
- TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers (AAAI 2025 · similarity 0.92)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.91)
- MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models (CVPR 2025 · similarity 0.91)
- Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.91)
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.
