Research map / 3D vision / Gaussian splatting
ST4R-Splat: Spatio-Temporal Referring Segmentation in 4D Gaussian Splatting
Yuming Meng, Dong Wu, Hongbin Zha
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 cross-modal attention module (ablation) | ST4R-Splat · HyperNeRF referring (time-agnostic) | mIoU (%): 58.56 -> 77.67 | Improved |
| add Gaussian-text contrastive loss (ablation) | ST4R-Splat · HyperNeRF referring (time-agnostic) | mIoU (%): 70.85 -> 77.67 | Improved |
| add instance-aware feature regularization loss (ablation) | ST4R-Splat · HyperNeRF referring (time-agnostic) | mIoU (%): 76.94 -> 77.67 | Improved |
| use instance-level temporal state mapping instead of rendering-based features for temporal queries in novel view | ST4R-Splat vs 4DLangSplat · HyperNeRF novel viewpoint, time-sensitive | Acc (%): 51.92 -> 90.38 | Improved |
| replace open-vocabulary 4D language field with instance-aware referring field and decoupled temporal mapping | 4DLangSplat · HyperNeRF time-sensitive queries | vIoU (%): 12.14 -> 57.98 | Improved |
| use instance-aware 4D referring field instead of ReferSplat adapted to 4D | ReferSplat · HyperNeRF time-agnostic | mIoU (%): 35.42 -> 77.67 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ReferSplat — ReferSplat: Referring Segmentation in 3D Gaussian Splatting (ICML 2025) · 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
- ReferSplat: Referring Segmentation in 3D Gaussian Splatting (ICML 2025 · similarity 0.91)
- 4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models (CVPR 2025 · similarity 0.89)
- Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting (NeurIPS 2025 · similarity 0.88)
- Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration (CVPR 2025 · similarity 0.88)
- SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting (NeurIPS 2025 · similarity 0.88)
- RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation (NeurIPS 2024 · similarity 0.88)
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.
