AI RESEARCH

Director: Instance-aware Gaussian Splatting for Dynamic Scene Modeling and Understanding

arXiv CS.CV

ArXi:2604.01678v1 Announce Type: new Volumetric video seeks to model dynamic scenes as temporally coherent 4D representations. While recent Gaussian-based approaches achieve impressive rendering fidelity, they primarily emphasize appearance but are largely agnostic to instance-level structure, limiting stable tracking and semantic reasoning in highly dynamic scenarios. In this paper, we present Director, a unified spatio-temporal Gaussian representation that jointly models human performance, high-fidelity rendering, and instance-level semantics.