Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhou, Guanyu, Yin, Yida, Chai, Wenhao, Tong, Shengbang, Fu, Xingyu, Liu, Zhuang
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.09531
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908952902500352
author Zhou, Guanyu
Yin, Yida
Chai, Wenhao
Tong, Shengbang
Fu, Xingyu
Liu, Zhuang
author_facet Zhou, Guanyu
Yin, Yida
Chai, Wenhao
Tong, Shengbang
Fu, Xingyu
Liu, Zhuang
contents Vision-language models (VLMs) still struggle with visual perception tasks such as spatial understanding and viewpoint recognition. One plausible contributing factor is that natural image datasets provide limited supervision for low-level visual skills. This motivates a practical question: can targeted synthetic supervision, generated from only a task keyword such as Depth Order, address these weaknesses? To investigate this question, we introduce VisionFoundry, a task-aware synthetic data generation pipeline that takes only the task name as input and uses large language models (LLMs) to generate questions, answers, and text-to-image (T2I) prompts, then synthesizes images with T2I models and verifies consistency with a proprietary VLM, requiring no reference images or human annotation. Using VisionFoundry, we construct VisionFoundry-10K, a synthetic visual question answering (VQA) dataset containing 10k image-question-answer triples spanning 10 tasks. Models trained on VisionFoundry-10K achieve substantial improvements on visual perception benchmarks: +7% on MMVP and +10% on CV-Bench-3D, while preserving broader capabilities and showing favorable scaling behavior as data size increases. Our results suggest that limited task-targeted supervision is an important contributor to this bottleneck and that synthetic supervision is a promising path toward more systematic training for VLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2604_09531
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images
Zhou, Guanyu
Yin, Yida
Chai, Wenhao
Tong, Shengbang
Fu, Xingyu
Liu, Zhuang
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Vision-language models (VLMs) still struggle with visual perception tasks such as spatial understanding and viewpoint recognition. One plausible contributing factor is that natural image datasets provide limited supervision for low-level visual skills. This motivates a practical question: can targeted synthetic supervision, generated from only a task keyword such as Depth Order, address these weaknesses? To investigate this question, we introduce VisionFoundry, a task-aware synthetic data generation pipeline that takes only the task name as input and uses large language models (LLMs) to generate questions, answers, and text-to-image (T2I) prompts, then synthesizes images with T2I models and verifies consistency with a proprietary VLM, requiring no reference images or human annotation. Using VisionFoundry, we construct VisionFoundry-10K, a synthetic visual question answering (VQA) dataset containing 10k image-question-answer triples spanning 10 tasks. Models trained on VisionFoundry-10K achieve substantial improvements on visual perception benchmarks: +7% on MMVP and +10% on CV-Bench-3D, while preserving broader capabilities and showing favorable scaling behavior as data size increases. Our results suggest that limited task-targeted supervision is an important contributor to this bottleneck and that synthetic supervision is a promising path toward more systematic training for VLMs.
title VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2604.09531