Papers › Solving Zero-Shot 3D Visual Grounding as Constraint Satisfaction Problems

Solving Zero-Shot 3D Visual Grounding as Constraint Satisfaction Problems

21 Nov 2024arXiv:2411.14594archive 2025-07-28

Qihao Yuan, Jiaming Zhang, Kailai Li, Rainer Stiefelhagen

3D visual grounding (3DVG) aims to locate objects in a 3D scene with natural language descriptions. Supervised methods have achieved decent accuracy, but have a closed vocabulary and limited language understanding ability. Zero-shot methods mostly utilize large language models (LLMs) to handle natural language descriptions, yet suffer from slow inference speed. To address these problems, in this work, we propose a zero-shot method that reformulates the 3DVG task as a Constraint Satisfaction Problem (CSP), where the variables and constraints represent objects and their spatial relations, respectively. This allows a global reasoning of all relevant objects, producing grounding results of both the target and anchor objects. Moreover, we demonstrate the flexibility of our framework by handling negation- and counting-based queries with only minor extra coding efforts. Our system, Constraint Satisfaction Visual Grounding (CSVG), has been extensively evaluated on the public datasets ScanRefer and Nr3D datasets using only open-source LLMs. Results show the effectiveness of CSVG and superior grounding accuracy over current state-of-the-art zero-shot 3DVG methods with improvements of +7.0% (Acc@0.5 score) and +11.2% on the ScanRefer and Nr3D datasets, respectively. The code of our system is publicly available at https://github.com/sunsleaf/CSVG.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

sunsleaf/csvg officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D visual groundingNegationVisual Grounding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections