Research map / 3D vision / Gaussian splatting
LangField4D: Learning Identity-Adaptive and Spatio-Temporal Continuous 4D Language Fields for Dynamic Scenes
Yichao Xu, Qiaowei Miao, Jinsheng Quan, Wei Yang, Zhihui Li, Yawei Luo
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 |
|---|---|---|---|
| replace MLP decoders with TetraPlane representation (ablation) | LangField4D (without IdaGG) · HyperNeRF time-varying | vIoU: 51.61 -> 60.03 | Improved |
| replace MLP decoders with TetraPlane representation (ablation) | LangField4D (without IdaGG) · HyperNeRF time-varying | Acc: 71.95 -> 80.97 | Improved |
| replace MLP decoders with TetraPlane representation (ablation) | LangField4D (without IdaGG) · HyperNeRF time-agnostic | mIoU: 80.85 -> 81.94 | Improved |
| add Identity-Adaptive Gaussian Grouping (ablation) | TetraPlane · HyperNeRF time-agnostic | mIoU: 81.94 -> 83.09 | Improved |
| add Identity-Adaptive Gaussian Grouping (ablation) | MLP decoders · HyperNeRF time-agnostic | mIoU: 80.85 -> 82.63 | Improved |
| add Identity-Adaptive Gaussian Grouping (ablation) | TetraPlane · HyperNeRF time-varying | vIoU: 60.03 -> 64.31 | Improved |
| add Identity-Adaptive Gaussian Grouping (ablation) | MLP decoders · HyperNeRF time-varying | Acc: 71.95 -> 70.79 | Hurt |
| add Identity-Adaptive Gaussian Grouping (ablation) | MLP decoders · HyperNeRF time-varying | vIoU: 51.61 -> 52.59 | Improved |
| add IdaGG on Gaussian identity (ablation) | TetraPlane · HyperNeRF time-agnostic | mAcc: 98.29 -> 98.37 | No clear effect |
| full LangField4D vs 4DLangSplat | 4DLangSplat · Neu3D time-agnostic | mIoU: 55.18 -> 71.62 | Improved |
| full LangField4D vs 4DLangSplat | 4DLangSplat · HyperNeRF time-sensitive (overall) | vIoU: 47.04 -> 64.31 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- LangSplat — LangSplat: 3D Language Gaussian Splatting (CVPR 2024) · better on 2 of 2 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
- 4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models (CVPR 2025 · similarity 0.90)
- Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding (NeurIPS 2025 · similarity 0.88)
- Thinking in Dynamics: How Multimodal Large Language Models Perceive, Track, and Reason Dynamics in Physical 4D World (CVPR 2026 · similarity 0.88)
- 4DP-QA: Scalable QA for 4D Perception in Vision Language Models (CVPR 2026 · similarity 0.87)
- 4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration (NeurIPS 2025 · similarity 0.86)
- ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation (CVPR 2026 · similarity 0.86)
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.
