Enhancing Spatial Understanding in Image Generation via Reward Modeling

Zhenyu Tang, Feng Chaoran, yfdeng, Jie Wu, Xiaojie Li, Rui Wang, Yunpeng Chen, Daquan Zhou

Enhancing Spatial Understanding in Image Generation via Reward Modeling: 60 upvotes on Hugging Face Daily Papers, #3 of 22 papers on 2026-03-02. Day-by-day upvote history.

Recent progress in text-to-image generation has greatly advanced visual fidelity and creativity, but it has also imposed higher demands on prompt complexity-particularly in encoding intricate spatial relationships. In such cases, achieving satisfactory results often requires multiple sampling attempts. To address this challenge, we introduce a novel method that strengthens the spatial understanding of current image generation models. We first construct the SpatialReward-Dataset with over 80k preference pairs. Building on this dataset, we build SpatialScore, a reward model designed to evaluate the accuracy of spatial relationships in text-to-image generation, achieving performance that even surpasses leading proprietary models on spatial evaluation. We further demonstrate that this reward model effectively enables online reinforcement learning for the complex spatial generation. Extensive experiments across multiple benchmarks show that our specialized reward model yields significant and consistent gains in spatial understanding for image generation.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.