{"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/separating-sounds-from-a-single-image","title":"Leveraging Category Information for Single-Frame Visual Sound Source Separation","arxiv_id":"2007.07984","date":"2020-07-15","proceeding":null,"authors":["Lingyu Zhu","Esa Rahtu"],"abstract":"Visual sound source separation aims at identifying sound components from a given sound mixture with the presence of visual cues. Prior works have demonstrated impressive results, but with the expense of large multi-stage architectures and complex data representations (e.g. optical flow trajectories). In contrast, we study simple yet efficient models for visual sound separation using only a single video frame. Furthermore, our models are able to exploit the information of the sound source category in the separation process. To this end, we propose two models where we assume that i) the category labels are available at the training time, or ii) we know if the training sample pairs are from the same or different category. The experiments with the MUSIC dataset show that our model obtains comparable or better performance compared to several recent baseline methods. The code is available at https://github.com/ly-zhu/Leveraging-Category-Information-for-Single-Frame-Visual-Sound-Source-Separation","url_abs":"https://arxiv.org/abs/2007.07984v2","url_pdf":"https://arxiv.org/pdf/2007.07984v2.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":"separating-sounds-from-a-single-image","repo_url":"https://github.com/ly-zhu/Leveraging-Category-Information-for-Single-Frame-Visual-Sound-Source-Separation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"separating-sounds-from-a-single-image","repo_url":"https://github.com/ly-zhu/Separating-Sounds-from-a-Single-Image","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"separating-sounds-from-a-single-image","repo_url":"https://github.com/ly-zhu/ly-zhu.github.io","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.07984","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.07984"}},"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/ly-zhu/ly-zhu.github.io","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ly-zhu/Separating-Sounds-from-a-Single-Image","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ly-zhu/Leveraging-Category-Information-for-Single-Frame-Visual-Sound-Source-Separation","reach":null}],"summary":{"ran_draft_wrong":2,"ran_honours":1,"unverified":9},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"listed":{"samples":10,"ran":1,"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":"18a0f2d0f82fbfea","entry":"load_checkpoint","repo":"ly-zhu/Leveraging-Category-Information-for-Single-Frame-Visual-Sound-Source-Separation","repo_kind":"official","path":"main_Appearance_Sound.py","file_url":"https://github.com/ly-zhu/Leveraging-Category-Information-for-Single-Frame-Visual-Sound-Source-Separation/blob/HEAD/main_Appearance_Sound.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"18a0f2d0f82fbfea"}},{"code_sha256_prefix":"5b434cdece8b83b2","entry":"load_checkpoint_from_train","repo":"ly-zhu/Leveraging-Category-Information-for-Single-Frame-Visual-Sound-Source-Separation","repo_kind":"official","path":"main_Appearance_Sound.py","file_url":"https://github.com/ly-zhu/Leveraging-Category-Information-for-Single-Frame-Visual-Sound-Source-Separation/blob/HEAD/main_Appearance_Sound.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5b434cdece8b83b2"}},{"code_sha256_prefix":"a4a08206de81190b","entry":"warpgrid","repo":"ly-zhu/Separating-Sounds-from-a-Single-Image","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/ly-zhu/Separating-Sounds-from-a-Single-Image/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a4a08206de81190b"}},{"code_sha256_prefix":"ce942a958c0ae909","entry":"convert_to_separable_conv","repo":"ly-zhu/Separating-Sounds-from-a-Single-Image","repo_kind":"listed","path":"models/_deeplab.py","file_url":"https://github.com/ly-zhu/Separating-Sounds-from-a-Single-Image/blob/HEAD/models/_deeplab.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":"ce942a958c0ae909"}},{"code_sha256_prefix":"7eaee91dfd40b5ae","entry":"load_checkpoint","repo":"ly-zhu/Separating-Sounds-from-a-Single-Image","repo_kind":"listed","path":"main_Appearance_att_Sound.py","file_url":"https://github.com/ly-zhu/Separating-Sounds-from-a-Single-Image/blob/HEAD/main_Appearance_att_Sound.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":"7eaee91dfd40b5ae"}},{"code_sha256_prefix":"42b20e91f34ebe8b","entry":"load_checkpoint","repo":"ly-zhu/Separating-Sounds-from-a-Single-Image","repo_kind":"listed","path":"main_CatEmb_Sound.py","file_url":"https://github.com/ly-zhu/Separating-Sounds-from-a-Single-Image/blob/HEAD/main_CatEmb_Sound.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":"42b20e91f34ebe8b"}},{"code_sha256_prefix":"fe139af98f1594db","entry":"load_checkpoint_from_train","repo":"ly-zhu/Separating-Sounds-from-a-Single-Image","repo_kind":"listed","path":"main_Appearance_att_Sound.py","file_url":"https://github.com/ly-zhu/Separating-Sounds-from-a-Single-Image/blob/HEAD/main_Appearance_att_Sound.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":"fe139af98f1594db"}},{"code_sha256_prefix":"5f67e6f9050256f6","entry":"load_checkpoint_from_train","repo":"ly-zhu/Separating-Sounds-from-a-Single-Image","repo_kind":"listed","path":"main_CatEmb_Sound.py","file_url":"https://github.com/ly-zhu/Separating-Sounds-from-a-Single-Image/blob/HEAD/main_CatEmb_Sound.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":"5f67e6f9050256f6"}},{"code_sha256_prefix":"e52e3c5bf79fea6f","entry":"magnitude2heatmap","repo":"ly-zhu/Separating-Sounds-from-a-Single-Image","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/ly-zhu/Separating-Sounds-from-a-Single-Image/blob/HEAD/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":"e52e3c5bf79fea6f"}},{"code_sha256_prefix":"5dce17dfe9cd12fe","entry":"recover_rgb","repo":"ly-zhu/Separating-Sounds-from-a-Single-Image","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/ly-zhu/Separating-Sounds-from-a-Single-Image/blob/HEAD/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":"5dce17dfe9cd12fe"}},{"code_sha256_prefix":"a707c39dcde29fcc","entry":"unet_conv","repo":"ly-zhu/Separating-Sounds-from-a-Single-Image","repo_kind":"listed","path":"models/audio_net.py","file_url":"https://github.com/ly-zhu/Separating-Sounds-from-a-Single-Image/blob/HEAD/models/audio_net.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":"a707c39dcde29fcc"}},{"code_sha256_prefix":"bf4439e420654360","entry":"unet_upconv","repo":"ly-zhu/Separating-Sounds-from-a-Single-Image","repo_kind":"listed","path":"models/audio_net.py","file_url":"https://github.com/ly-zhu/Separating-Sounds-from-a-Single-Image/blob/HEAD/models/audio_net.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":"bf4439e420654360"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}