Research map / 3D vision / Gaussian splatting
Click-Gaussian: Interactive Segmentation to Any 3D Gaussians
Seokhun Choi, Hyeonseop Song, Jaechul Kim, Taehyeong Kim, Hoseok Do
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 Global Feature-guided Learning loss (ablation) | Click-Gaussian · LERF-Mask fine level | mIoU: 42.3 -> 84.3 | Improved |
| add GFL loss (ablation) | Click-Gaussian · LERF-Mask all objects | mIoU: 58.6 -> 85.4 | Improved |
| add granularity prior (fine feature includes coarse feature) (ablation) | Click-Gaussian · LERF-Mask fine level | mIoU: 78.3 -> 84.3 | Improved |
| add hypersphere (3D-norm) regularization (ablation) | Click-Gaussian · LERF-Mask fine level | mIoU: 74.1 -> 84.3 | Improved |
| add spatial consistency regularization (ablation) | Click-Gaussian · LERF-Mask fine level | mIoU: 78.5 -> 84.3 | Improved |
| add rendered feature (2D-norm) regularization (ablation) | Click-Gaussian · LERF-Mask coarse level | mIoU: 89.3 -> 89.1 coarse; 80.8 -> 84.3 fine | Mixed |
| use two-level masks instead of three-level-area masks (ablation) | Click-Gaussian · LERF-Mask | mIoU | Improved |
| assign fine mask by smallest segment (area) instead of highest score segment (ablation) | three-level masks · LERF-Mask fine level | mIoU | Improved |
| Click-Gaussian versus GARField on Ramen fine level | Click-Gaussian · LERF-Mask Ramen fine | mIoU: 86.9 (GARField) vs 86.7 | No clear effect |
| replace SAM-decoder and post-processing methods with feature-field clusters | Click-Gaussian · SPIn-NeRF | mIoU: 88.0 -> 94.0 | 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.
- GARField — GARField: Group Anything with Radiance Fields (CVPR 2024) · better on 4 of 5 shared results
- OmniSeg3D — OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning (CVPR 2024) · better on 3 of 3 shared results
- SAGA — SAGA: Stochastic Whole-Body Grasping with Contact (ECCV 2022) · 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
- GaussianCut: Interactive segmentation via graph cut for 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.91)
- AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation (ICLR 2024 · similarity 0.89)
- iSegMan: Interactive Segment-and-Manipulate 3D Gaussians (CVPR 2025 · similarity 0.88)
- Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes (ICML 2025 · similarity 0.88)
- Segment Any 3D Gaussians (AAAI 2025 · similarity 0.87)
- Segment then Splat: Unified 3D Open-Vocabulary Segmentation via 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.
