{"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/leanvae-an-ultra-efficient-reconstruction-vae","title":"LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models","arxiv_id":"2503.14325","date":"2025-03-18","proceeding":null,"authors":["Yu Cheng","Fajie Yuan"],"abstract":"Recent advances in Latent Video Diffusion Models (LVDMs) have revolutionized video generation by leveraging Video Variational Autoencoders (Video VAEs) to compress intricate video data into a compact latent space. However, as LVDM training scales, the computational overhead of Video VAEs becomes a critical bottleneck, particularly for encoding high-resolution videos. To address this, we propose LeanVAE, a novel and ultra-efficient Video VAE framework that introduces two key innovations: (1) a lightweight architecture based on a Neighborhood-Aware Feedforward (NAF) module and non-overlapping patch operations, drastically reducing computational cost, and (2) the integration of wavelet transforms and compressed sensing techniques to enhance reconstruction quality. Extensive experiments validate LeanVAE's superiority in video reconstruction and generation, particularly in enhancing efficiency over existing Video VAEs. Our model offers up to 50x fewer FLOPs and 44x faster inference speed while maintaining competitive reconstruction quality, providing insights for scalable, efficient video generation. Our models and code are available at https://github.com/westlake-repl/LeanVAE","url_abs":"https://arxiv.org/abs/2503.14325v1","url_pdf":"https://arxiv.org/pdf/2503.14325v1.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":"leanvae-an-ultra-efficient-reconstruction-vae","repo_url":"https://github.com/westlake-repl/leanvae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"video-generation","task_name":"Video Generation"},{"task_slug":"video-reconstruction","task_name":"Video Reconstruction"},{"task_slug":"compressed-sensing","task_name":"compressed sensing"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-generation-on-sky-time-lapse","task":"Video Generation","dataset":"Sky Time-lapse","model":"Latte + LeanVAE","rank_in_archive_order":2,"of":9,"metrics":{"FVD 16":"49.59"},"uses_additional_data":false},{"leaderboard":"/sota/video-generation-on-ucf-101","task":"Video Generation","dataset":"UCF-101","model":"Latte + LeanVAE","rank_in_archive_order":13,"of":48,"metrics":{"FVD16":"164.45"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.14325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14325"}},"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/westlake-repl/leanvae","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/westlakerepl/LeanVAE","reach":{"status":"gone","observed_at":"2026-09-16","how":"tree_404+repo_404"}}],"summary":{"ran":2,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"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":"f1e8ae723c3a8928","entry":"DiagonalGaussianDistribution","repo":"westlake-repl/leanvae","repo_kind":"official","path":"LeanVAE/models/autoencoder.py","file_url":"https://github.com/westlake-repl/leanvae/blob/HEAD/LeanVAE/models/autoencoder.py","link_basis":"first_harvest_node","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":"f1e8ae723c3a8928"}},{"code_sha256_prefix":"a6420573e931d240","entry":"Patcher","repo":"westlake-repl/leanvae","repo_kind":"official","path":"LeanVAE/models/autoencoder.py","file_url":"https://github.com/westlake-repl/leanvae/blob/HEAD/LeanVAE/models/autoencoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a6420573e931d240"}},{"code_sha256_prefix":"3ddac6b65bcfb042","entry":"LeanVAE","repo":"westlake-repl/leanvae","repo_kind":"official","path":"LeanVAE/models/autoencoder.py","file_url":"https://github.com/westlake-repl/leanvae/blob/HEAD/LeanVAE/models/autoencoder.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":"3ddac6b65bcfb042"}},{"code_sha256_prefix":"24a5260bd069131d","entry":"UnPatcher","repo":"westlake-repl/leanvae","repo_kind":"official","path":"LeanVAE/models/autoencoder.py","file_url":"https://github.com/westlake-repl/leanvae/blob/HEAD/LeanVAE/models/autoencoder.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":"24a5260bd069131d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}