Research map / 3D vision / Gaussian splatting
IndoorSplat: Enhanced Indoor Scene Reconstruction with Structured 2D Gaussian Splatting
Min Shi, Tao Yang, Xigang Zhao, Qi Wang, Dengming Zhu, Zhaoxin Li
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 MASt3R-SfM initialization instead of COLMAP (ablation) | IndoorSplat · ScanNet | F1 (5cm): 0.6572 -> 0.7587 | Improved |
| add MASt3R-SfM initialization instead of COLMAP (ablation) | IndoorSplat · ScanNet++ | F1 (5cm): 0.8192 -> 0.8967 | Improved |
| add dense initialization strategy (ablation) | IndoorSplat · ScanNet | F1 (5cm): 0.7369 -> 0.7587 | Improved |
| add dense initialization strategy (ablation) | IndoorSplat · ScanNet++ | F1 (5cm): 0.8831 -> 0.8967 | Improved |
| add monocular depth supervision (ablation) | IndoorSplat · ScanNet | F1 (5cm): 0.7491 -> 0.7587 | Improved |
| add monocular depth supervision (ablation) | IndoorSplat · ScanNet++ | F1 (5cm): 0.8829 -> 0.8967 | Improved |
| add monocular normal supervision (ablation) | IndoorSplat · ScanNet | F1 (5cm): 0.7251 -> 0.7587 | Improved |
| add monocular normal supervision (ablation) | IndoorSplat · ScanNet++ | F1 (5cm): 0.8385 -> 0.8967 | Improved |
| add iterative adaptive densification and L1 opacity regularization (ablation) | IndoorSplat · ScanNet | F1 (5cm): 0.7517 -> 0.7587 | Improved |
| add iterative adaptive densification and L1 opacity regularization (ablation) | IndoorSplat · ScanNet++ | F1 (5cm): 0.8779 -> 0.8967 | Improved |
| replace COLMAP with MASt3R initialization in 2DGS | 2DGS · ScanNet | F1 (5cm): 0.4514 -> 0.6368 | Improved |
| replace COLMAP with MASt3R initialization in 2DGS | 2DGS · ScanNet++ | F1 (5cm): 0.5978 -> 0.7792 | Improved |
Closest papers by meaning
- IndoorGS: Geometric Cues Guided Gaussian Splatting for Indoor Scene Reconstruction (CVPR 2025 · similarity 0.94)
- AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians (NeurIPS 2025 · similarity 0.91)
- PlanarGS: High-Fidelity Indoor 3D Gaussian Splatting Guided by Vision-Language Planar Priors (NeurIPS 2025 · similarity 0.91)
- EAP-GS: Efficient Augmentation of Pointcloud for 3D Gaussian Splatting in Few-shot Scene Reconstruction (CVPR 2025 · similarity 0.90)
- FreeSplat: Generalizable 3D Gaussian Splatting Towards Free View Synthesis of Indoor Scenes (NeurIPS 2024 · similarity 0.90)
- SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language 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.
