Research map / 3D vision / Gaussian splatting
OnlinePG: Online Open-Vocabulary Panoptic Mapping with 3D Gaussian Splatting
Hongjia Zhai, Qi Zhang, Xiaokun Pan, Xiyu Zhang, Yitong Dong, Huaqi Zhang, Dan Xu, Guofeng Zhang
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 bidirectional bipartite matching instead of nearest-neighbor matching (ablation) | OnlinePG global map fusion · ScanNetV2 | PRQ (T) / PRQ (S): +13.3 PRQ (T), +18.8 PRQ (S) | Improved |
| add backward verification to forward-only matching (ablation) | OnlinePG global map fusion · ScanNetV2 | PRQ (S): 38.40 -> 41.81 | Improved |
| add forward matching to backward-only matching (ablation) | OnlinePG global map fusion · ScanNetV2 | PRQ (T): 33.71 -> 37.97 | Improved |
| add forward matching to backward-only matching (ablation) | OnlinePG global map fusion · ScanNetV2 | PRQ (S): 42.72 -> 41.81 | Hurt |
| add segment clustering over sliding window (ablation) | OnlinePG · ScanNetV2 | PRQ (T) / PRQ (S): 32.25 -> 37.97 PRQ (T); 30.68 -> 41.81 PRQ (S) | Improved |
| add segment clustering over sliding window (ablation) | OnlinePG · ScanNetV2 | mIoU: 48.48 -> 48.48 | No clear effect |
| add voxel language feature grid (ablation) | OnlinePG · ScanNetV2 | mIoU: 30.40 -> 48.48 | Improved |
| add voxel language feature grid (ablation) | OnlinePG · ScanNetV2 | PRQ (S): 24.92 -> 41.81 | Improved |
| use multi-cue instead of single-cue graph clustering (ablation) | OnlinePG segment clustering · ScanNetV2 | PRQ: 8 to 18 PRQ improvement, ~40 ms extra latency | Improved |
| use coarser feature grid resolution than 5 cm (ablation) | OnlinePG feature grid · ScanNetV2 | performance: coarser than 5 cm | Hurt |
| compare OnlinePG with online baseline OnlineAnySeg | OnlinePG · ScanNetV2 | mIoU / mAcc.: 31.28 -> 48.48 mIoU; 52.20 -> 66.01 mAcc. | Improved |
| compare OnlinePG with offline PanoGS | OnlinePG · ScanNetV2 | mIoU: 50.72 -> 48.48 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 4 on most shared results.
- PanoGS — PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding (CVPR 2025) · better on 2 of 5 shared results
- LangSplat — LangSplat: 3D Language Gaussian Splatting (CVPR 2024) · better on 2 of 2 shared results
- O2V-Mapping — O2V-Mapping: Online Open-Vocabulary Mapping with Neural Implicit Representation (ECCV 2024) · better on 2 of 2 shared results
- OpenScene — OpenScene: 3D Scene Understanding With Open Vocabularies (CVPR 2023) · better on 1 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
- PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding (CVPR 2025 · similarity 0.89)
- ReferSplat: Referring Segmentation in 3D Gaussian Splatting (ICML 2025 · similarity 0.87)
- Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting (NeurIPS 2025 · similarity 0.87)
- PanoWorld: Towards Spatial Supersensing in 360◦ Panorama World (NeurIPS 2026 · similarity 0.87)
- Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding (CVPR 2025 · similarity 0.87)
- Tackling View-Dependent Semantics in 3D Language Gaussian Splatting (ICML 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.
