# SeqVLM: Proposal-Guided Multi-View Sequences Reasoning via VLM for Zero-Shot 3D Visual Grounding

arXiv: https://arxiv.org/abs/2508.20758 · HTML: https://mlsanity.com/paper/2508.20758/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 8 of its 61 references that are in the map.
- First posted on arXiv 28 Aug 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 8 of 8)

- [MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning](https://mlsanity.com/paper/2310.09478/) (2023)
- [Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI](https://mlsanity.com/paper/2407.06886/) (2024)
- [Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes](https://mlsanity.com/paper/2308.08769/) (2023)
- [SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding](https://mlsanity.com/paper/2412.04383/) (2024)
- [VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding](https://mlsanity.com/paper/2410.13860/) (2024)
- [FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow](https://mlsanity.com/paper/2306.00180/) (2023)
- [A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs](https://mlsanity.com/paper/2412.03324/) (2024)
- [Reasoning3D -- Grounding and Reasoning in 3D: Fine-Grained Zero-Shot Open-Vocabulary 3D Reasoning Part Segmentation via Large Vision-Language Models](https://mlsanity.com/paper/2405.19326/) (2024)

## Built on by (most cited first, 7 of 7)

- [UniGround: Universal 3D Visual Grounding via Training-Free Scene Parsing](https://mlsanity.com/paper/2603.08131/) (2026)
- [Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual Grounding](https://mlsanity.com/paper/2604.00528/) (2026)
- [HiSC: Hierarchical Spatial Clustering Token Compression for Efficient 3D Scene Understanding](https://mlsanity.com/paper/2608.04610/) (2026)
- [OpenGround: Planning-based Online Perception for Open-World 3D Visual Grounding](https://mlsanity.com/paper/2512.23020/) (2025)
- [Multiple Consistent 2D-3D Mappings for Robust Zero-Shot 3D Visual Grounding](https://mlsanity.com/paper/2604.26261/) (2026)
- [Agentic Collaborative Cognition for Zero-Shot 3D Understanding](https://mlsanity.com/paper/2606.24649/) (2026)
- [Where to Look Matters: Learning Influential Views for VLM-based 3D Visual Grounding](https://mlsanity.com/paper/2609.04741/) (2026)

## Abstract (arXiv)

3D Visual Grounding (3DVG) aims to localize objects in 3D scenes using natural language descriptions. Although supervised methods achieve higher accuracy in constrained settings, zero-shot 3DVG holds greater promise for real-world applications since eliminating scene-specific training requirements. However, existing zero-shot methods face challenges of spatial-limited reasoning due to reliance on single-view localization, and contextual omissions or detail degradation. To address these issues, we propose SeqVLM, a novel zero-shot 3DVG framework that leverages multi-view real-world scene images with spatial information for target object reasoning. Specifically, SeqVLM first generates 3D instance proposals via a 3D semantic segmentation network and refines them through semantic filtering, retaining only semantic-relevant candidates. A proposal-guided multi-view projection strategy then projects these candidate proposals onto real scene image sequences, preserving spatial relationships and contextual details in the conversion process of 3D point cloud to images. Furthermore, to mitigate VLM computational overload, we implement a dynamic scheduling mechanism that iteratively processes sequances-query prompts, leveraging VLM's cross-modal reasoning capabilities to identify textually specified objects. Experiments on the ScanRefer and Nr3D benchmarks demonstrate state-of-the-art performance, achieving Acc@0.25 scores of 55.6% and 53.2%, surpassing previous zero-shot methods by 4.0% and 5.2%, respectively, which advance 3DVG toward greater generalization and real-world applicability. The code is available at https://github.com/JiawLin/SeqVLM.