{"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/diffusion-autoencoders-toward-a-meaningful","title":"Diffusion Autoencoders: Toward a Meaningful and Decodable Representation","arxiv_id":"2111.15640","date":"2021-11-30","proceeding":"CVPR 2022 1","authors":["Konpat Preechakul","Nattanat Chatthee","Suttisak Wizadwongsa","Supasorn Suwajanakorn"],"abstract":"Diffusion probabilistic models (DPMs) have achieved remarkable quality in image generation that rivals GANs'. But unlike GANs, DPMs use a set of latent variables that lack semantic meaning and cannot serve as a useful representation for other tasks. This paper explores the possibility of using DPMs for representation learning and seeks to extract a meaningful and decodable representation of an input image via autoencoding. Our key idea is to use a learnable encoder for discovering the high-level semantics, and a DPM as the decoder for modeling the remaining stochastic variations. Our method can encode any image into a two-part latent code, where the first part is semantically meaningful and linear, and the second part captures stochastic details, allowing near-exact reconstruction. This capability enables challenging applications that currently foil GAN-based methods, such as attribute manipulation on real images. We also show that this two-level encoding improves denoising efficiency and naturally facilitates various downstream tasks including few-shot conditional sampling. Please visit our project page: https://Diff-AE.github.io/","url_abs":"https://arxiv.org/abs/2111.15640v3","url_pdf":"https://arxiv.org/pdf/2111.15640v3.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":"diffusion-autoencoders-toward-a-meaningful","repo_url":"https://github.com/phizaz/diffae","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"diffusion-autoencoders-toward-a-meaningful","repo_url":"https://github.com/chethankodase/alma","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"diffusion-autoencoders-toward-a-meaningful","repo_url":"https://github.com/naserdamer/mordiff","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.15640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.15640"}},"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/phizaz/diffae","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chethankodase/alma","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/naserdamer/mordiff","reach":{"status":"ok"}}],"summary":{"ran":6,"unverified":9},"by_repo_kind":{"official":{"samples":15,"ran":6,"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":"f36fb3b9b1239da0","entry":"resize_and_convert","repo":"phizaz/diffae","repo_kind":"official","path":"data_resize_bedroom.py","file_url":"https://github.com/phizaz/diffae/blob/HEAD/data_resize_bedroom.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f36fb3b9b1239da0"}},{"code_sha256_prefix":"89da1a2395b0d0d9","entry":"resize_and_convert","repo":"phizaz/diffae","repo_kind":"official","path":"data_resize_celebahq.py","file_url":"https://github.com/phizaz/diffae/blob/HEAD/data_resize_celebahq.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89da1a2395b0d0d9"}},{"code_sha256_prefix":"b6e307e73df01911","entry":"resize_multiple","repo":"phizaz/diffae","repo_kind":"official","path":"data_resize_bedroom.py","file_url":"https://github.com/phizaz/diffae/blob/HEAD/data_resize_bedroom.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b6e307e73df01911"}},{"code_sha256_prefix":"2a2ae041586bbc78","entry":"resize_multiple","repo":"phizaz/diffae","repo_kind":"official","path":"data_resize_celebahq.py","file_url":"https://github.com/phizaz/diffae/blob/HEAD/data_resize_celebahq.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a2ae041586bbc78"}},{"code_sha256_prefix":"a046145c828624ad","entry":"resize_worker","repo":"phizaz/diffae","repo_kind":"official","path":"data_resize_bedroom.py","file_url":"https://github.com/phizaz/diffae/blob/HEAD/data_resize_bedroom.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a046145c828624ad"}},{"code_sha256_prefix":"8b346c500755d6bc","entry":"unpack_bz2","repo":"phizaz/diffae","repo_kind":"official","path":"align.py","file_url":"https://github.com/phizaz/diffae/blob/HEAD/align.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8b346c500755d6bc"}},{"code_sha256_prefix":"235265a7a3a652fb","entry":"chunk_size","repo":"phizaz/diffae","repo_kind":"official","path":"dist_utils.py","file_url":"https://github.com/phizaz/diffae/blob/HEAD/dist_utils.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":"235265a7a3a652fb"}},{"code_sha256_prefix":"f93f74df8c200466","entry":"get_file","repo":"phizaz/diffae","repo_kind":"official","path":"align.py","file_url":"https://github.com/phizaz/diffae/blob/HEAD/align.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":"f93f74df8c200466"}},{"code_sha256_prefix":"3436fefeb3a4b49a","entry":"jsonable","repo":"phizaz/diffae","repo_kind":"official","path":"config_base.py","file_url":"https://github.com/phizaz/diffae/blob/HEAD/config_base.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":"3436fefeb3a4b49a"}},{"code_sha256_prefix":"7b0f30c49d628c72","entry":"make_transform","repo":"phizaz/diffae","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/phizaz/diffae/blob/HEAD/dataset.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":"7b0f30c49d628c72"}},{"code_sha256_prefix":"f5b22953cffc5be7","entry":"resize_and_convert","repo":"phizaz/diffae","repo_kind":"official","path":"data_resize_celeba.py","file_url":"https://github.com/phizaz/diffae/blob/HEAD/data_resize_celeba.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":"f5b22953cffc5be7"}},{"code_sha256_prefix":"43751210df99f10f","entry":"resize_multiple","repo":"phizaz/diffae","repo_kind":"official","path":"data_resize_celeba.py","file_url":"https://github.com/phizaz/diffae/blob/HEAD/data_resize_celeba.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":"43751210df99f10f"}},{"code_sha256_prefix":"0cf07ac3798b588b","entry":"resize_worker","repo":"phizaz/diffae","repo_kind":"official","path":"data_resize_celeba.py","file_url":"https://github.com/phizaz/diffae/blob/HEAD/data_resize_celeba.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":"0cf07ac3798b588b"}},{"code_sha256_prefix":"4d7a82e3c9b47997","entry":"resize_worker","repo":"phizaz/diffae","repo_kind":"official","path":"data_resize_celebahq.py","file_url":"https://github.com/phizaz/diffae/blob/HEAD/data_resize_celebahq.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":"4d7a82e3c9b47997"}},{"code_sha256_prefix":"96226a66ab62eb91","entry":"use_cached_dataset_path","repo":"phizaz/diffae","repo_kind":"official","path":"dataset_util.py","file_url":"https://github.com/phizaz/diffae/blob/HEAD/dataset_util.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":"96226a66ab62eb91"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}