{"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/a-unified-prompt-guided-in-context-inpainting","title":"LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model","arxiv_id":"2305.11577","date":"2023-05-19","proceeding":"CVPR 2024 1","authors":["Chenjie Cao","Yunuo Cai","Qiaole Dong","Yikai Wang","Yanwei Fu"],"abstract":"This paper introduces LeftRefill, an innovative approach to efficiently harness large Text-to-Image (T2I) diffusion models for reference-guided image synthesis. As the name implies, LeftRefill horizontally stitches reference and target views together as a whole input. The reference image occupies the left side, while the target canvas is positioned on the right. Then, LeftRefill paints the right-side target canvas based on the left-side reference and specific task instructions. Such a task formulation shares some similarities with contextual inpainting, akin to the actions of a human painter. This novel formulation efficiently learns both structural and textured correspondence between reference and target without other image encoders or adapters. We inject task and view information through cross-attention modules in T2I models, and further exhibit multi-view reference ability via the re-arranged self-attention modules. These enable LeftRefill to perform consistent generation as a generalized model without requiring test-time fine-tuning or model modifications. Thus, LeftRefill can be seen as a simple yet unified framework to address reference-guided synthesis. As an exemplar, we leverage LeftRefill to address two different challenges: reference-guided inpainting and novel view synthesis, based on the pre-trained StableDiffusion. Codes and models are released at https://github.com/ewrfcas/LeftRefill.","url_abs":"https://arxiv.org/abs/2305.11577v3","url_pdf":"https://arxiv.org/pdf/2305.11577v3.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":"a-unified-prompt-guided-in-context-inpainting","repo_url":"https://github.com/ewrfcas/arci","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-unified-prompt-guided-in-context-inpainting","repo_url":"https://github.com/ewrfcas/leftrefill","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-unified-prompt-guided-in-context-inpainting","repo_url":"https://github.com/ewrfcas/pgic_inpainting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-inpainting","task_name":"Image Inpainting"},{"task_slug":"image-manipulation","task_name":"Image Manipulation"},{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"pixel-prediction","method_name":"Inpainting"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.11577","atlas_url":"https://app.syntology.ai/?focus=2305.11577","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}