{"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/spatial-broadcast-decoder-a-simple","title":"Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs","arxiv_id":"1901.07017","date":"2019-01-21","proceeding":null,"authors":["Nicholas Watters","Loic Matthey","Christopher P. Burgess","Alexander Lerchner"],"abstract":"We present a simple neural rendering architecture that helps variational autoencoders (VAEs) learn disentangled representations. Instead of the deconvolutional network typically used in the decoder of VAEs, we tile (broadcast) the latent vector across space, concatenate fixed X- and Y-\"coordinate\" channels, and apply a fully convolutional network with 1x1 stride. This provides an architectural prior for dissociating positional from non-positional features in the latent distribution of VAEs, yet without providing any explicit supervision to this effect. We show that this architecture, which we term the Spatial Broadcast decoder, improves disentangling, reconstruction accuracy, and generalization to held-out regions in data space. It provides a particularly dramatic benefit when applied to datasets with small objects. We also emphasize a method for visualizing learned latent spaces that helped us diagnose our models and may prove useful for others aiming to assess data representations. Finally, we show the Spatial Broadcast Decoder is complementary to state-of-the-art (SOTA) disentangling techniques and when incorporated improves their performance.","url_abs":"https://arxiv.org/abs/1901.07017v2","url_pdf":"https://arxiv.org/pdf/1901.07017v2.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":"spatial-broadcast-decoder-a-simple","repo_url":"https://github.com/deepmind/spriteworld","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"spatial-broadcast-decoder-a-simple","repo_url":"https://github.com/google-deepmind/spriteworld","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"spatial-broadcast-decoder-a-simple","repo_url":"https://github.com/lukaszbinden/spatial-broadcast-decoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"spatial-broadcast-decoder-a-simple","repo_url":"https://github.com/mmrl/lost-in-latent-space","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"neural-rendering","task_name":"Neural Rendering"}],"methods":[{"method_slug":"sbd","method_name":"Spatial Broadcast Decoder"}],"datasets_introduced":[],"methods_introduced":[{"slug":"sbd","name":"Spatial Broadcast Decoder","full_name":"Spatial Broadcast Decoder"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.07017","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.07017"}},"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/google-deepmind/spriteworld","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deepmind/spriteworld","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mmrl/lost-in-latent-space","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lukaszbinden/spatial-broadcast-decoder","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"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":"2c20b50e95a15493","entry":"decoder_sbd","repo":"lukaszbinden/spatial-broadcast-decoder","repo_kind":"listed","path":"sbd.py","file_url":"https://github.com/lukaszbinden/spatial-broadcast-decoder/blob/HEAD/sbd.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":"2c20b50e95a15493"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}