Pith. sign in

REVIEW 5 cited by

SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.13438 v5 pith:NFFS5B6Z submitted 2024-03-18 cs.CV

Chenyang Ma , Kai Lu , Ta-Ying Cheng , Niki Trigoni , Andrew Markham This is my paper
classification cs.CV
keywords spatialcapabilitiescurrentinteractingmodelsplanningpriorsprompting
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Current state-of-the-art spatial reasoning-enhanced VLMs are trained to excel at spatial visual question answering (VQA). However, we believe that higher-level 3D-aware tasks, such as articulating dynamic scene changes and motion planning, require a fundamental and explicit 3D understanding beyond current spatial VQA datasets. In this work, we present SpatialPIN, a framework designed to enhance the spatial reasoning capabilities of VLMs through prompting and interacting with priors from multiple 3D foundation models in a zero-shot, training-free manner. Extensive experiments demonstrate that our spatial reasoning-imbued VLM performs well on various forms of spatial VQA and can extend to help in various downstream robotics tasks such as pick and stack and trajectory planning.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Visual Credit Audit for Multimodal Spatial Reasoning

    cs.CV 2026-07 conditional novelty 6.0 of 10

    VCA finds 12.73–26.25% of spatial decisions are correct yet uncredited by the image, and separates marginal image support from relation-specific visual response.

  2. SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL

    cs.CV 2025-12 conditional novelty 6.0 of 10

    A two-phase interactive RL framework (DIRL) lets a 3B VLM learn to coordinate multiple vision and robot tools, reaching top benchmark scores and 86% real-robot pick-and-place success.

  3. AntiGrounding: Lifting Robotic Actions into VLM Representation Space for Decision Making

    cs.RO 2025-06 conditional novelty 6.0 of 10

    AntiGrounding lifts candidate robot trajectories into the VLM's visual space via multi-view rendering and structured VQA, and reports 57.5% average success across eight manipulation tasks, beating three intermediate-r...

  4. The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework

    cs.CV 2025-05 conditional novelty 5.0 of 10

    A VLM-LLM agentic pipeline and a new 251-person benchmark show that ordinary personal photo sets can reveal private attributes, including abstract traits like income and MBTI, at rates above human evaluators.

  5. Enhancing Spatial Reasoning in Vision-Language Models via Chain-of-Thought Prompting and Reinforcement Learning

    cs.CV 2025-07 conditional novelty 4.0 of 10

    Scene-graph-based chain-of-thought prompting and GRPO training improve spatial reasoning accuracy in vision-language models, and GRPO degrades less than supervised fine-tuning when question wording is flipped.

Pith tools