REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language Models

TL;DR

This paper introduces REVISION, a rendering-based framework that enhances spatial reasoning in vision-language models by generating accurate synthetic images, improving spatial fidelity and reasoning capabilities in multimodal tasks.

Contribution

The paper presents REVISION, a novel 3D rendering pipeline that improves spatial fidelity in vision-language models and introduces RevQA, a benchmark for spatial reasoning evaluation.

Findings

REVISION improves spatial consistency across models.

Synthetic images from REVISION enhance training-free spatial reasoning.

State-of-the-art models show limited robustness in complex spatial reasoning.

Abstract

Text-to-Image (T2I) and multimodal large language models (MLLMs) have been adopted in solutions for several computer vision and multimodal learning tasks. However, it has been found that such vision-language models lack the ability to correctly reason over spatial relationships. To tackle this shortcoming, we develop the REVISION framework which improves spatial fidelity in vision-language models. REVISION is a 3D rendering based pipeline that generates spatially accurate synthetic images, given a textual prompt. REVISION is an extendable framework, which currently supports 100+ 3D assets, 11 spatial relationships, all with diverse camera perspectives and backgrounds. Leveraging images from REVISION as additional guidance in a training-free manner consistently improves the spatial consistency of T2I models across all spatial relationships, achieving competitive performance on the VISOR and T2I-CompBench benchmarks. We also design RevQA, a question-answering benchmark to evaluate the spatial reasoning abilities of MLLMs, and find that state-of-the-art models are not robust to complex spatial reasoning under adversarial settings. Our results and findings indicate that utilizing rendering-based frameworks is an effective approach for developing spatially-aware generative models.