ReferGaussian grounds language queries in 4D Gaussian scenes without per-scene semantic training

arXivarXivPapers

ReferGaussian grounds language queries in 4D Gaussian scenes without per-scene semantic training
arXiv / Bangpu Chen, Yaxuan Li and colleagues

Bangpu Chen, Yaxuan Li, Shirui Peng and colleagues study Referring 4D Gaussian Splatting, a task for grounding temporally varying, multi-target, reasoning-intensive and zero-target expressions in dynamic 4D scenes, and introduce the R4D-Bench-QA benchmark. Their framework, ReferGaussian, is built on 4DGS and organizes mask-supported Gaussian entities in an EntityBank; multimodal large language models decompose complex queries into trackable object phrases and structured constraints, and constraint-aware grounding runs without scene-specific semantic optimization.

On R4D-Bench-QA and the 4D LangSplat protocol, the authors report improved temporal target selection and competitive spatiotemporal grounding without scene-specific semantic training. The paper is accepted at ACM Multimedia 2026.