Skip to content
Preprint

TDVR: Joint Text Disambiguation and Viewpoint Reasoning for Zero-Shot 3D Visual Grounding

Aug 2026 · 0 citations · 43 references
Computer Science

TL;DR

This work proposes TDVR, a training-free reasoning framework that disambiguates the input text and infers accurate viewpoints for zero-shot 3D visual grounding, and outperforms the existing state-of-the-art methods in addressing ambiguous query text and deficient viewpoints.

Abstract

Zero-shot 3D visual grounding aims to localize specific objects based on textual descriptions and 3D visual input. However, the effectiveness of existing methods is significantly hindered by the ambiguous query text and deficient viewpoints. To address these issues, we propose TDVR, a training-free reasoning framework that disambiguates the input text and infers accurate viewpoints for zero-shot 3D visual grounding. First, we construct semantic 3D scene graph from the detected instances in the 3D point cloud. Subsequently, we put the original query, appearance and spatial relationship descriptions into the LLM for fusion, thereby disambiguating the initial input. We leverage chain-of-thought reasoning to generate the structured representation of disambiguated query. Then taking the scene graph and structured query as input, we get the optimal view via viewpoint reasoning to solve the problem of missing viewpoints during grounding. Based on the obtained optimal viewpoint, we further discriminate the distracting objects, enabling the model with the ability to distinguish similar instances. After that, we match the category text and appearance images with the query by computing the similarity of feature vectors. Finally, the target object was identified by integrating the viewpoint score, confusion score, category score, and appearance score. Compared with previous methods, our TDVR has stronger capabilities in viewpoint reasoning, similar object discrimination, and ambiguous query understanding. Experimental results on the public ScanRefer dataset show that our method outperforms the existing state-of-the-art methods by 15.25% and 14.46% in Acc@0.25 and Acc@0.5 respectively, demonstrating the effectiveness of our TDVR in addressing ambiguous query text and deficient viewpoints.

View source

Similar papers

Preprint Aug 2026

ID-VTG: Image-Disambiguated Video Temporal Grounding

The Visually-Guided Disambiguation Aggregation Aggregation (VGD-Agg) framework is proposed, a framework based on a dual-branch fast-slow architecture that enhances discriminability via two learnable tokens and achieves state-of-the-art results on the proposed benchmarks.

Minghang Zheng, Jing Wei, Hong-Yi Yang et al. · 0 citations
Sep 2026

Enhancing target identification and query discrimination for visual grounding

FSG-AID is presented, which integrates fine-grained semantic guidance with an attribute-aware iterative decoder and jointly exploits visual and language features to mine attribute semantics, initialize the target query, and iteratively refine the target representation.

Xiya Bu, Yu Liu, Jizhe Yu et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Where, How, and When: Query-Guided Grounding for Video Understanding

Understanding video content requires reasoning at multiple levels of granularity, from identifying objects to interpreting their interactions and localizing when specific actions occur. This thesis studies three query-guided grounding tasks that answer where key objects are (object-level grounding), how they interact (...

Yogesh Kumar · 0 citations
Preprint Sep 2026

Where to Look Matters: Learning Influential Views for VLM-based 3D Visual Grounding

Recent zero-shot 3D visual grounding methods leverage vision-language models (VLMs) to localize objects in 3D scenes from natural language queries. However, these methods typically rely on heuristic rules to select which camera views are provided to the VLM, often prioritizing object visibility rather than grounding re...

Tsung-Chih Chiang, Hsuan-Kung Yang, Jou-Min Liu et al. · 0 citations
#artificial intelligence Preprint Oct 2026

BridgeAfford: Bridging Query-Target Gap for Generalizable 3D Affordance Grounding

Cross-object alignment among geometrically similar interaction regions during training enables structures on unseen objects that resemble previously observed ones to produce representations similar to those learned during training, facilitating target-region recognition.

Yi-Jie Su, Ya-Kun Zhu, Yi Bin et al. · 0 citations
#machine learning Preprint Oct 2026

What Words Keep of a Place: Zero-Shot Language Reasoning for Cross-View Geo-Localization

Cross-view geo-localization is commonly solved as an image retrieval problem, matching a ground-level image against a database of satellite tiles through a jointly trained embedding. Such models are accurate, but they need large paired supervision and cannot show what evidence supports a match. In this paper, we study...

Ayesh Abu Lehyeh, J. Jung, Safwan Wshah · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.