{"ID":2857859,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.07721","arxiv_id":"2510.07721","title":"RePainter: Empowering E-commerce Object Removal via Spatial-matting Reinforcement Learning","abstract":"In web data, product images are central to boosting user engagement and advertising efficacy on e-commerce platforms, yet the intrusive elements such as watermarks and promotional text remain major obstacles to delivering clear and appealing product visuals. Although diffusion-based inpainting methods have advanced, they still face challenges in commercial settings due to unreliable object removal and limited domain-specific adaptation. To tackle these challenges, we propose Repainter, a reinforcement learning framework that integrates spatial-matting trajectory refinement with Group Relative Policy Optimization (GRPO). Our approach modulates attention mechanisms to emphasize background context, generating higher-reward samples and reducing unwanted object insertion. We also introduce a composite reward mechanism that balances global, local, and semantic constraints, effectively reducing visual artifacts and reward hacking. Additionally, we contribute EcomPaint-100K, a high-quality, large-scale e-commerce inpainting dataset, and a standardized benchmark EcomPaint-Bench for fair evaluation. Extensive experiments demonstrate that Repainter significantly outperforms state-of-the-art methods, especially in challenging scenes with intricate compositions. We will release our code and weights upon acceptance.","short_abstract":"In web data, product images are central to boosting user engagement and advertising efficacy on e-commerce platforms, yet the intrusive elements such as watermarks and promotional text remain major obstacles to delivering clear and appealing product visuals. Although diffusion-based inpainting methods have advanced, th...","url_abs":"https://arxiv.org/abs/2510.07721","url_pdf":"https://arxiv.org/pdf/2510.07721v1","authors":"[\"Zipeng Guo\",\"Lichen Ma\",\"Xiaolong Fu\",\"Gaojing Zhou\",\"Lan Yang\",\"Yuchen Zhou\",\"Linkai Liu\",\"Yu He\",\"Ximan Liu\",\"Shiping Dong\",\"Jingling Fu\",\"Zhen Chen\",\"Yu Shi\",\"Junshi Huang\",\"Jason Li\",\"Chao Gou\"]","published":"2025-10-09T02:57:33Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Reinforcement Learning\",\"Diffusion Model\"]","has_code":false}