Research map / 3D vision / Gaussian splatting
IGFuse: Interactive 3D Gaussian Scene Reconstruction via Multi-Scans Fusion
Wenhao Hu, Zesheng Li, Haonan Zhou, Liu Liu, Xuexiang Wen, Zhizhong Su, Xi Li, Gaoang Wang
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 collaborative co-pruning to bidirectional alignment (ablation) | IGFuse · Synthetic dataset | PSNR: 35.10 -> 35.55 | Improved |
| add pseudo-state guided alignment (ablation) | IGFuse · Synthetic dataset | PSNR: 35.55 -> 36.93 | Improved |
| add pseudo-state supervision (ablation) | IGFuse · Synthetic 1 scene (G1) | PSNR: 37.04 -> 39.26 | Improved |
| add pseudo-state supervision (ablation) | IGFuse · Synthetic 2 scene (G1) | PSNR: 37.51 -> 37.59 | Improved |
| add pseudo-state supervision (ablation) | IGFuse · Synthetic 2 scene (G2) | PSNR: 36.14 -> 37.50 | Improved |
| replace multi-stage segmentation and inpainting with multi-scan fusion | DecoupledGaussian · Real-world dataset | PSNR: 22.28 -> 27.18 | Improved |
| add 2D inpainting to segmentation-only methods | Gaussian segmentation baselines · Synthetic vs real-world scenes | PSNR | Mixed |
| train beyond about 5000 iterations per scan (ablation) | IGFuse · Real-world scenes | PSNR | No clear effect |
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.
- DecoupledGaussian — DecoupledGaussian: Object-Scene Decoupling for Physics-Based Interaction (CVPR 2025) · better on 4 of 4 shared results
- Gaussiancut — GaussianCut: Interactive segmentation via graph cut for 3D Gaussian Splatting (NeurIPS 2024) · better on 3 of 3 shared results
- Gaussian Grouping — Gaussian Grouping: Segment and Edit Anything in 3D Scenes (ECCV 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 0.88)
- Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting (ICLR 2025 · similarity 0.88)
- No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images (ICLR 2025 · similarity 0.88)
- CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene Reconstruction (NeurIPS 2026 · similarity 0.88)
- PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting for Novel View Synthesis (ICML 2025 · similarity 0.87)
- Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting (NeurIPS 2025 · similarity 0.87)
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.
