UniFunc3D: Unified Active Spatial-Temporal Grounding for 3D Functionality Segmentation
This addresses the challenge of fragmented pipelines and visual blindness in 3D scene understanding for agents, representing a strong specific gain rather than incremental.
The paper tackles the problem of 3D functionality segmentation by grounding natural-language instructions into precise masks, achieving state-of-the-art performance with a 59.9% relative mIoU improvement on SceneFun3D without task-specific training.
Functionality segmentation in 3D scenes requires an agent to ground implicit natural-language instructions into precise masks of fine-grained interactive elements. Existing methods rely on fragmented pipelines that suffer from visual blindness during initial task parsing. We observe that these methods are limited by single-scale, passive and heuristic frame selection. We present UniFunc3D, a unified and training-free framework that treats the multimodal large language model as an active observer. By consolidating semantic, temporal, and spatial reasoning into a single forward pass, UniFunc3D performs joint reasoning to ground task decomposition in direct visual evidence. Our approach introduces active spatial-temporal grounding with a coarse-to-fine strategy. This allows the model to select correct video frames adaptively and focus on high-detail interactive parts while preserving the global context necessary for disambiguation. On SceneFun3D, UniFunc3D achieves state-of-the-art performance, surpassing both training-free and training-based methods by a large margin with a relative 59.9\% mIoU improvement, without any task-specific training. Code will be released on our project page: https://jiaying.link/unifunc3d.