QVR3D: Query-Guided Visual Reasoning for Training-Free 3D Grounding
cs.CV
Submitted: 2026-10-31
Updated: 2026-10-31
Journal ref: WACV 2027
Code: https://github.com/jwliao1209/QVR3D
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: 3D visual grounding localizes objects in 3D scenes from natural language descriptions, requiring reasoning over semantics, spatial relationships, and multi-view observations.
Terminology
Abstract
3D visual grounding localizes objects in 3D scenes from natural language descriptions, requiring reasoning over semantics, spatial relationships, and multi-view observations. Training-free approaches avoid costly annotations but often rely on explicit scene transformation or scene-level frame selection, which may waste limited visual capacity on query-irrelevant regions. We observe that effective grounding should prioritize observations that provide evidence for the query rather than uniformly represent the entire scene. Based on this insight, we introduce QVR3D, a query-guided visual reasoning framework that operates on RGB-D observations using off-the-shelf foundation models. QVR3D combines Query-Guided Maximum Coverage (QGMC) for selecting complementary query-relevant views with Grounding Probability Estimation (GPE) that integrates instance confidence, attribute consistency, and relationship consistency. The framework supports both single- and multi-object grounding without task-specific adaptation. Experiments on ScanRefer and Nr3D achieve state-of-the-art zero-shot performance, while QGMC also improves frame efficiency across multiple 3D vision-language tasks. Our code is available at https://github.com/jwliao1209/QVR3D.
Sources
- Qwen3-VL Technical Report
- Grounded 3D-LLM with Referent Tokens
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs