{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/poem-precise-object-level-editing-via-mllm","title":"POEM: Precise Object-level Editing via MLLM control","arxiv_id":"2504.08111","date":"2025-04-10","proceeding":null,"authors":["Marco Schouten","Mehmet Onurcan Kaya","Serge Belongie","Dim P. Papadopoulos"],"abstract":"Diffusion models have significantly improved text-to-image generation, producing high-quality, realistic images from textual descriptions. Beyond generation, object-level image editing remains a challenging problem, requiring precise modifications while preserving visual coherence. Existing text-based instructional editing methods struggle with localized shape and layout transformations, often introducing unintended global changes. Image interaction-based approaches offer better accuracy but require manual human effort to provide precise guidance. To reduce this manual effort while maintaining a high image editing accuracy, in this paper, we propose POEM, a framework for Precise Object-level Editing using Multimodal Large Language Models (MLLMs). POEM leverages MLLMs to analyze instructional prompts and generate precise object masks before and after transformation, enabling fine-grained control without extensive user input. This structured reasoning stage guides the diffusion-based editing process, ensuring accurate object localization and transformation. To evaluate our approach, we introduce VOCEdits, a benchmark dataset based on PASCAL VOC 2012, augmented with instructional edit prompts, ground-truth transformations, and precise object masks. Experimental results show that POEM outperforms existing text-based image editing approaches in precision and reliability while reducing manual effort compared to interaction-based methods.","url_abs":"https://arxiv.org/abs/2504.08111v1","url_pdf":"https://arxiv.org/pdf/2504.08111v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-based-image-editing","task_name":"Text-based Image Editing"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[],"datasets_introduced":[{"slug":"vocedits","name":"VOCEdits","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}