Reinforcement learning improves multi image editing consistency
DeCoRL: Decomposed Consistency Reinforcement Learning for Multi-Image Composition
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
Editing images using several reference pictures at once is hard because keeping everything consistent across images is tricky. The paper presents a new approach called DeCoRL that teaches a model to focus on each object separately when combining images, so it keeps the details right. It uses a special reward system that checks object-level accuracy and helps the model learn better. They also created a new benchmark to test how well models can combine from two to six images, showing improved results.
What this means in practice
- •For graphic design teams: Enhance large scale image editing tools to keep object details consistent when merging multiple reference images for complex compositions.$Commercial implications: Enables advanced commercial image editing software to reliably handle multiple-image compositions, improving product quality and user control.
- •For multimedia content creators: Improve the quality of automatically generated composite images when using multiple source pictures in content creation workflows.
Authors
Zhiqiang Wu, Shuang Sun, Jiale Zhang, Jing Li, Yibo Chen, Xu Tang, Yao Hu
Abstract
Multi-image composition (MICo) is a critical yet challenging capability for large-scale image editing models, where consistency degrades rapidly as the number of reference images increases. While supervised fine-tuning (SFT) can equip models with basic MICo ability, it provides only implicit supervision on the composed image and often fails to learn reliable object-level correspondence across multiple references. We propose DeCoRL, a reinforcement-learning (RL) framework that improves MICo consistency by decomposing holistic MICo consistency into object-level consistency. DeCoRL first establishes instruction-relevant object correspondences across reference images and localizes the corresponding regions in the generated image. It then uses a VLM-based reward model trained on single-object consistency annotations to produce fine-grained, object-wise feedback, which is aggregated into a multi-object consistency reward to guide RL post-training. We further introduce DeCo-Bench, a benchmark covering compositions from 2 to 6 reference images. Experiments on DeCo-Bench and the public MICo-Bench demonstrate consistent improvements in MICo consistency.