{"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/perceptual-generative-autoencoders","title":"Perceptual Generative Autoencoders","arxiv_id":"1906.10335","date":"2019-06-25","proceeding":"ICML 2020 1","authors":["Zijun Zhang","Ruixiang Zhang","Zongpeng Li","Yoshua Bengio","Liam Paull"],"abstract":"Modern generative models are usually designed to match target distributions directly in the data space, where the intrinsic dimension of data can be much lower than the ambient dimension. We argue that this discrepancy may contribute to the difficulties in training generative models. We therefore propose to map both the generated and target distributions to a latent space using the encoder of a standard autoencoder, and train the generator (or decoder) to match the target distribution in the latent space. Specifically, we enforce the consistency in both the data space and the latent space with theoretically justified data and latent reconstruction losses. The resulting generative model, which we call a perceptual generative autoencoder (PGA), is then trained with a maximum likelihood or variational autoencoder (VAE) objective. With maximum likelihood, PGAs generalize the idea of reversible generative models to unrestricted neural network architectures and arbitrary number of latent dimensions. When combined with VAEs, PGAs substantially improve over the baseline VAEs in terms of sample quality. Compared to other autoencoder-based generative models using simple priors, PGAs achieve state-of-the-art FID scores on CIFAR-10 and CelebA.","url_abs":"https://arxiv.org/abs/1906.10335v2","url_pdf":"https://arxiv.org/pdf/1906.10335v2.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":"perceptual-generative-autoencoders","repo_url":"https://github.com/zj10/PGA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"perceptual-generative-autoencoders","repo_url":"https://github.com/rosinality/lvpga-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.10335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.10335"}},"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/rosinality/lvpga-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zj10/PGA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":11},"by_repo_kind":{"official":{"samples":11,"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":"744bd707d0fa38ac","entry":"calculate_activation_statistics","repo":"zj10/PGA","repo_kind":"official","path":"src/fid.py","file_url":"https://github.com/zj10/PGA/blob/HEAD/src/fid.py","link_basis":"first_harvest_node","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":"744bd707d0fa38ac"}},{"code_sha256_prefix":"b6f978273b6c7b7c","entry":"calculate_frechet_distance","repo":"zj10/PGA","repo_kind":"official","path":"src/fid.py","file_url":"https://github.com/zj10/PGA/blob/HEAD/src/fid.py","link_basis":"first_harvest_node","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":"b6f978273b6c7b7c"}},{"code_sha256_prefix":"eed7dfe6d7eb4968","entry":"directory","repo":"zj10/PGA","repo_kind":"official","path":"src/pylib/path.py","file_url":"https://github.com/zj10/PGA/blob/HEAD/src/pylib/path.py","link_basis":"first_harvest_node","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":"eed7dfe6d7eb4968"}},{"code_sha256_prefix":"b4a0e3033db188f4","entry":"float2im","repo":"zj10/PGA","repo_kind":"official","path":"src/imlib/dtype.py","file_url":"https://github.com/zj10/PGA/blob/HEAD/src/imlib/dtype.py","link_basis":"first_harvest_node","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":"b4a0e3033db188f4"}},{"code_sha256_prefix":"7da8feb6cb76e81a","entry":"float2uint","repo":"zj10/PGA","repo_kind":"official","path":"src/imlib/dtype.py","file_url":"https://github.com/zj10/PGA/blob/HEAD/src/imlib/dtype.py","link_basis":"first_harvest_node","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":"7da8feb6cb76e81a"}},{"code_sha256_prefix":"f3156e8742e34851","entry":"get_activations","repo":"zj10/PGA","repo_kind":"official","path":"src/fid.py","file_url":"https://github.com/zj10/PGA/blob/HEAD/src/fid.py","link_basis":"first_harvest_node","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":"f3156e8742e34851"}},{"code_sha256_prefix":"d9b8413d4ecbe399","entry":"immerge","repo":"zj10/PGA","repo_kind":"official","path":"src/imlib/transform.py","file_url":"https://github.com/zj10/PGA/blob/HEAD/src/imlib/transform.py","link_basis":"first_harvest_node","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":"d9b8413d4ecbe399"}},{"code_sha256_prefix":"9f280946211388f6","entry":"imread","repo":"zj10/PGA","repo_kind":"official","path":"src/imlib/basic.py","file_url":"https://github.com/zj10/PGA/blob/HEAD/src/imlib/basic.py","link_basis":"first_harvest_node","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":"9f280946211388f6"}},{"code_sha256_prefix":"87a498cbec79e938","entry":"name","repo":"zj10/PGA","repo_kind":"official","path":"src/pylib/path.py","file_url":"https://github.com/zj10/PGA/blob/HEAD/src/pylib/path.py","link_basis":"first_harvest_node","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":"87a498cbec79e938"}},{"code_sha256_prefix":"ded2db9b11b1035e","entry":"split","repo":"zj10/PGA","repo_kind":"official","path":"src/pylib/path.py","file_url":"https://github.com/zj10/PGA/blob/HEAD/src/pylib/path.py","link_basis":"first_harvest_node","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":"ded2db9b11b1035e"}},{"code_sha256_prefix":"c75a52b1e074ded6","entry":"to_range","repo":"zj10/PGA","repo_kind":"official","path":"src/imlib/dtype.py","file_url":"https://github.com/zj10/PGA/blob/HEAD/src/imlib/dtype.py","link_basis":"first_harvest_node","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":"c75a52b1e074ded6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}