Paper
UniGround: Universal 3D Visual Grounding via Training-Free Scene Parsing
Authors
Jiaxi Zhang, Yunheng Wang, Wei Lu, Taowen Wang, Weisheng Xu, Shuning Zhang, Yixiao Feng, Yuetong Fang, Renjing Xu
Abstract
Understanding and localizing objects in complex 3D environments from natural language descriptions, known as 3D Visual Grounding (3DVG), is a foundational challenge in embodied AI, with broad implications for robotics, augmented reality, and human-machine interaction. Large-scale pre-trained foundation models have driven significant progress on this front, enabling open-vocabulary 3DVG that allows systems to locate arbitrary objects in a given scene. However, their reliance on pre-trained models constrains 3D perception and reasoning within the inherited knowledge boundaries, resulting in limited generalization to unseen spatial relationships and poor robustness to out-of-distribution scenes. In this paper, we replace this constrained perception with training-free visual and geometric reasoning, thereby unlocking open-world 3DVG that enables the localization of any object in any scene beyond the training data. Specifically, the proposed UniGround operates in two stages: a Global Candidate Filtering stage that constructs scene candidates through training-free 3D topology and multi-view semantic encoding, and a Local Precision Grounding stage that leverages multi-scale visual prompting and structured reasoning to precisely identify the target object. Experiments on ScanRefer and EmbodiedScan show that UniGround achieves 46.1\%/34.1\% Acc@0.25/0.5 on ScanRefer and 28.7\% Acc@0.25 on EmbodiedScan, establishing a new state-of-the-art among zero-shot methods on EmbodiedScan without any 3D supervision. We further evaluate UniGround in real-world environments under uncontrolled reconstruction conditions and substantial domain shift, showing training-free reasoning generalizes robustly beyond curated benchmarks.
Metadata
Related papers
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin, Kaixuan Fan, Yilei Jian... • 2026-03-30
On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers
Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or • 2026-03-30
Graphilosophy: Graph-Based Digital Humanities Computing with The Four Books
Minh-Thu Do, Quynh-Chau Le-Tran, Duc-Duy Nguyen-Mai, Thien-Trang Nguyen, Khan... • 2026-03-30
ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining
Anuj Diwan, Eunsol Choi, David Harwath • 2026-03-30
RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems
Oliver Aleksander Larsen, Mahyar T. Moghaddam • 2026-03-30
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.08131v1</id>\n <title>UniGround: Universal 3D Visual Grounding via Training-Free Scene Parsing</title>\n <updated>2026-03-09T09:10:01Z</updated>\n <link href='https://arxiv.org/abs/2603.08131v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.08131v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Understanding and localizing objects in complex 3D environments from natural language descriptions, known as 3D Visual Grounding (3DVG), is a foundational challenge in embodied AI, with broad implications for robotics, augmented reality, and human-machine interaction. Large-scale pre-trained foundation models have driven significant progress on this front, enabling open-vocabulary 3DVG that allows systems to locate arbitrary objects in a given scene. However, their reliance on pre-trained models constrains 3D perception and reasoning within the inherited knowledge boundaries, resulting in limited generalization to unseen spatial relationships and poor robustness to out-of-distribution scenes. In this paper, we replace this constrained perception with training-free visual and geometric reasoning, thereby unlocking open-world 3DVG that enables the localization of any object in any scene beyond the training data. Specifically, the proposed UniGround operates in two stages: a Global Candidate Filtering stage that constructs scene candidates through training-free 3D topology and multi-view semantic encoding, and a Local Precision Grounding stage that leverages multi-scale visual prompting and structured reasoning to precisely identify the target object. Experiments on ScanRefer and EmbodiedScan show that UniGround achieves 46.1\\%/34.1\\% Acc@0.25/0.5 on ScanRefer and 28.7\\% Acc@0.25 on EmbodiedScan, establishing a new state-of-the-art among zero-shot methods on EmbodiedScan without any 3D supervision. We further evaluate UniGround in real-world environments under uncontrolled reconstruction conditions and substantial domain shift, showing training-free reasoning generalizes robustly beyond curated benchmarks.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.RO'/>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n <published>2026-03-09T09:10:01Z</published>\n <arxiv:comment>14 pages,6 figures,3 tables</arxiv:comment>\n <arxiv:primary_category term='cs.RO'/>\n <author>\n <name>Jiaxi Zhang</name>\n </author>\n <author>\n <name>Yunheng Wang</name>\n </author>\n <author>\n <name>Wei Lu</name>\n </author>\n <author>\n <name>Taowen Wang</name>\n </author>\n <author>\n <name>Weisheng Xu</name>\n </author>\n <author>\n <name>Shuning Zhang</name>\n </author>\n <author>\n <name>Yixiao Feng</name>\n </author>\n <author>\n <name>Yuetong Fang</name>\n </author>\n <author>\n <name>Renjing Xu</name>\n </author>\n </entry>"
}