{"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/high-fidelity-pluralistic-image-completion","title":"High-Fidelity Pluralistic Image Completion with Transformers","arxiv_id":"2103.14031","date":"2021-03-25","proceeding":"ICCV 2021 10","authors":["Ziyu Wan","Jingbo Zhang","Dongdong Chen","Jing Liao"],"abstract":"Image completion has made tremendous progress with convolutional neural networks (CNNs), because of their powerful texture modeling capacity. However, due to some inherent properties (e.g., local inductive prior, spatial-invariant kernels), CNNs do not perform well in understanding global structures or naturally support pluralistic completion. Recently, transformers demonstrate their power in modeling the long-term relationship and generating diverse results, but their computation complexity is quadratic to input length, thus hampering the application in processing high-resolution images. This paper brings the best of both worlds to pluralistic image completion: appearance prior reconstruction with transformer and texture replenishment with CNN. The former transformer recovers pluralistic coherent structures together with some coarse textures, while the latter CNN enhances the local texture details of coarse priors guided by the high-resolution masked images. The proposed method vastly outperforms state-of-the-art methods in terms of three aspects: 1) large performance boost on image fidelity even compared to deterministic completion methods; 2) better diversity and higher fidelity for pluralistic completion; 3) exceptional generalization ability on large masks and generic dataset, like ImageNet.","url_abs":"https://arxiv.org/abs/2103.14031v1","url_pdf":"https://arxiv.org/pdf/2103.14031v1.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":"high-fidelity-pluralistic-image-completion","repo_url":"https://github.com/karynaur/High-Fidelity-Pluralistic-ICT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"high-fidelity-pluralistic-image-completion","repo_url":"https://github.com/karynaur/ICT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"high-fidelity-pluralistic-image-completion","repo_url":"https://github.com/raywzy/ICT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"high-fidelity-pluralistic-image-completion","repo_url":"https://github.com/yangyucheng000/ICT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-inpainting","task_name":"Image Inpainting"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-inpainting-on-celeba-hq","task":"Image Inpainting","dataset":"CelebA-HQ","model":"ICT","rank_in_archive_order":6,"of":6,"metrics":{"FID":"12.84","P-IDS":"0.13","U-IDS":"0.58"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.14031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.14031"}},"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/karynaur/ICT","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/raywzy/ICT","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangyucheng000/ICT","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/karynaur/High-Fidelity-Pluralistic-ICT","reach":null}],"summary":{"ran":7,"unverified":1},"by_repo_kind":{"listed":{"samples":8,"ran":7,"repositories":2}},"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":8,"samples":[{"code_sha256_prefix":"69cf3439b6b654f7","entry":"Block","repo":"karynaur/High-Fidelity-Pluralistic-ICT","repo_kind":"listed","path":"transformer/model.py","file_url":"https://github.com/karynaur/High-Fidelity-Pluralistic-ICT/blob/HEAD/transformer/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"69cf3439b6b654f7"}},{"code_sha256_prefix":"545f9243b2c67d16","entry":"Block","repo":"raywzy/ICT","repo_kind":"listed","path":"Transformer/models/model.py","file_url":"https://github.com/raywzy/ICT/blob/HEAD/Transformer/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"545f9243b2c67d16"}},{"code_sha256_prefix":"f7536f907ea35f6f","entry":"Block_2","repo":"raywzy/ICT","repo_kind":"listed","path":"Transformer/models/model.py","file_url":"https://github.com/raywzy/ICT/blob/HEAD/Transformer/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f7536f907ea35f6f"}},{"code_sha256_prefix":"fb2f67ff573fae6f","entry":"CausalSelfAttention","repo":"karynaur/High-Fidelity-Pluralistic-ICT","repo_kind":"listed","path":"transformer/model.py","file_url":"https://github.com/karynaur/High-Fidelity-Pluralistic-ICT/blob/HEAD/transformer/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fb2f67ff573fae6f"}},{"code_sha256_prefix":"4e88ff3b87c736b3","entry":"CausalSelfAttention","repo":"raywzy/ICT","repo_kind":"listed","path":"Transformer/models/model.py","file_url":"https://github.com/raywzy/ICT/blob/HEAD/Transformer/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4e88ff3b87c736b3"}},{"code_sha256_prefix":"4240f6d5bd6a9fb5","entry":"GELU2","repo":"raywzy/ICT","repo_kind":"listed","path":"Transformer/models/model.py","file_url":"https://github.com/raywzy/ICT/blob/HEAD/Transformer/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4240f6d5bd6a9fb5"}},{"code_sha256_prefix":"2c0fddb7b833a3e0","entry":"GPT","repo":"karynaur/High-Fidelity-Pluralistic-ICT","repo_kind":"listed","path":"transformer/model.py","file_url":"https://github.com/karynaur/High-Fidelity-Pluralistic-ICT/blob/HEAD/transformer/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2c0fddb7b833a3e0"}},{"code_sha256_prefix":"3e55e40a74985ee9","entry":"GPT","repo":"raywzy/ICT","repo_kind":"listed","path":"Transformer/models/model.py","file_url":"https://github.com/raywzy/ICT/blob/HEAD/Transformer/models/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3e55e40a74985ee9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}