{"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/smartbrush-text-and-shape-guided-object","title":"SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model","arxiv_id":"2212.05034","date":"2022-12-09","proceeding":"CVPR 2023 1","authors":["Shaoan Xie","Zhifei Zhang","Zhe Lin","Tobias Hinz","Kun Zhang"],"abstract":"Generic image inpainting aims to complete a corrupted image by borrowing surrounding information, which barely generates novel content. By contrast, multi-modal inpainting provides more flexible and useful controls on the inpainted content, \\eg, a text prompt can be used to describe an object with richer attributes, and a mask can be used to constrain the shape of the inpainted object rather than being only considered as a missing area. We propose a new diffusion-based model named SmartBrush for completing a missing region with an object using both text and shape-guidance. While previous work such as DALLE-2 and Stable Diffusion can do text-guided inapinting they do not support shape guidance and tend to modify background texture surrounding the generated object. Our model incorporates both text and shape guidance with precision control. To preserve the background better, we propose a novel training and sampling strategy by augmenting the diffusion U-net with object-mask prediction. Lastly, we introduce a multi-task training strategy by jointly training inpainting with text-to-image generation to leverage more training data. We conduct extensive experiments showing that our model outperforms all baselines in terms of visual quality, mask controllability, and background preservation.","url_abs":"https://arxiv.org/abs/2212.05034v1","url_pdf":"https://arxiv.org/pdf/2212.05034v1.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":"smartbrush-text-and-shape-guided-object","repo_url":"https://github.com/IjustAi/smartbrush","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-inpainting","task_name":"Image Inpainting"},{"task_slug":"object","task_name":"Object"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"pixel-prediction","method_name":"Inpainting"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.05034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.05034"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IjustAi/smartbrush","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"listed":{"samples":6,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"e49736e635e1b058","entry":"GaussianBlur","repo":"IjustAi/smartbrush","repo_kind":"listed","path":"different_level_mask.py","file_url":"https://github.com/IjustAi/smartbrush/blob/HEAD/different_level_mask.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e49736e635e1b058"}},{"code_sha256_prefix":"24d143d26588a76c","entry":"denoise_add_noise","repo":"IjustAi/smartbrush","repo_kind":"listed","path":"inference.py","file_url":"https://github.com/IjustAi/smartbrush/blob/HEAD/inference.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"24d143d26588a76c"}},{"code_sha256_prefix":"a7ed024ebd7024e4","entry":"norm_all","repo":"IjustAi/smartbrush","repo_kind":"listed","path":"utilities.py","file_url":"https://github.com/IjustAi/smartbrush/blob/HEAD/utilities.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a7ed024ebd7024e4"}},{"code_sha256_prefix":"9f00ea8fe4d9f1e4","entry":"norm_torch","repo":"IjustAi/smartbrush","repo_kind":"listed","path":"utilities.py","file_url":"https://github.com/IjustAi/smartbrush/blob/HEAD/utilities.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f00ea8fe4d9f1e4"}},{"code_sha256_prefix":"a306fca9ef2be022","entry":"plot_sample","repo":"IjustAi/smartbrush","repo_kind":"listed","path":"inference.py","file_url":"https://github.com/IjustAi/smartbrush/blob/HEAD/inference.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a306fca9ef2be022"}},{"code_sha256_prefix":"ddb47af5d9933018","entry":"unorm","repo":"IjustAi/smartbrush","repo_kind":"listed","path":"utilities.py","file_url":"https://github.com/IjustAi/smartbrush/blob/HEAD/utilities.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ddb47af5d9933018"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}