Saved in:
Bibliographic Details
Main Authors: Lin, Jiaying, Xu, Dan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.23478
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912980861452288
author Lin, Jiaying
Xu, Dan
author_facet Lin, Jiaying
Xu, Dan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_23478
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle UniFunc3D: Unified Active Spatial-Temporal Grounding for 3D Functionality Segmentation
Lin, Jiaying
Xu, Dan
Computer Vision and Pattern Recognition
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.
title UniFunc3D: Unified Active Spatial-Temporal Grounding for 3D Functionality Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.23478