Paper · arXiv 2602.24233
Enhancing Spatial Understanding in Image Generation via Reward Modeling
Zhenyu Tang, Chaoran Feng, Yufan Deng, Jie Wu, Xiaojie Li, Rui Wang, Yunpeng Chen, Daquan Zhou
A new reward model called SpatialScore is introduced to improve spatial relationship understanding in text-to-image generation through reinforcement learning with a large-scale dataset of preference pairs.
Abstract
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.