{"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/vision-guided-and-mask-enhanced-adaptive","title":"Vision-guided and Mask-enhanced Adaptive Denoising for Prompt-based Image Editing","arxiv_id":"2410.10496","date":"2024-10-14","proceeding":null,"authors":["Kejie Wang","Xuemeng Song","Meng Liu","Jin Yuan","Weili Guan"],"abstract":"Text-to-image diffusion models have demonstrated remarkable progress in synthesizing high-quality images from text prompts, which boosts researches on prompt-based image editing that edits a source image according to a target prompt. Despite their advances, existing methods still encounter three key issues: 1) limited capacity of the text prompt in guiding target image generation, 2) insufficient mining of word-to-patch and patch-to-patch relationships for grounding editing areas, and 3) unified editing strength for all regions during each denoising step. To address these issues, we present a Vision-guided and Mask-enhanced Adaptive Editing (ViMAEdit) method with three key novel designs. First, we propose to leverage image embeddings as explicit guidance to enhance the conventional textual prompt-based denoising process, where a CLIP-based target image embedding estimation strategy is introduced. Second, we devise a self-attention-guided iterative editing area grounding strategy, which iteratively exploits patch-to-patch relationships conveyed by self-attention maps to refine those word-to-patch relationships contained in cross-attention maps. Last, we present a spatially adaptive variance-guided sampling, which highlights sampling variances for critical image regions to promote the editing capability. Experimental results demonstrate the superior editing capacity of ViMAEdit over all existing methods.","url_abs":"https://arxiv.org/abs/2410.10496v2","url_pdf":"https://arxiv.org/pdf/2410.10496v2.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":[{"paper_slug":"vision-guided-and-mask-enhanced-adaptive","repo_url":"https://github.com/Null-0000/ViMAEdit","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"text-based-image-editing","task_name":"Text-based Image Editing"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-based-image-editing-on-pie-bench","task":"Text-based Image Editing","dataset":"PIE-Bench","model":"Virtual Inversion+ViMAEdit","rank_in_archive_order":3,"of":18,"metrics":{"Background LPIPS":"45.67","Background PSNR":"28.27","CLIPSIM":"25.91","Structure Distance":"12.65"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.10496","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}