{"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/audio-synchronized-visual-animation","title":"Audio-Synchronized Visual Animation","arxiv_id":"2403.05659","date":"2024-03-08","proceeding":null,"authors":["Lin Zhang","Shentong Mo","Yijing Zhang","Pedro Morgado"],"abstract":"Current visual generation methods can produce high quality videos guided by texts. However, effectively controlling object dynamics remains a challenge. This work explores audio as a cue to generate temporally synchronized image animations. We introduce Audio Synchronized Visual Animation (ASVA), a task animating a static image to demonstrate motion dynamics, temporally guided by audio clips across multiple classes. To this end, we present AVSync15, a dataset curated from VGGSound with videos featuring synchronized audio visual events across 15 categories. We also present a diffusion model, AVSyncD, capable of generating dynamic animations guided by audios. Extensive evaluations validate AVSync15 as a reliable benchmark for synchronized generation and demonstrate our models superior performance. We further explore AVSyncDs potential in a variety of audio synchronized generation tasks, from generating full videos without a base image to controlling object motions with various sounds. We hope our established benchmark can open new avenues for controllable visual generation. More videos on project webpage https://lzhangbj.github.io/projects/asva/asva.html.","url_abs":"https://arxiv.org/abs/2403.05659v2","url_pdf":"https://arxiv.org/pdf/2403.05659v2.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":"audio-synchronized-visual-animation","repo_url":"https://github.com/lzhangbj/ASVA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[{"slug":"avsync15","name":"AVSync15","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.05659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05659"}},"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/lzhangbj/ASVA","reach":{"status":"ok"}}],"summary":{"ran":8,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":13,"ran":9,"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":13,"samples":[{"code_sha256_prefix":"6ff9e4452d58338d","entry":"center_compact_sample","repo":"lzhangbj/ASVA","repo_kind":"official","path":"avsync/data.py","file_url":"https://github.com/lzhangbj/ASVA/blob/HEAD/avsync/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6ff9e4452d58338d"}},{"code_sha256_prefix":"dc842b5d99a54208","entry":"cov","repo":"lzhangbj/ASVA","repo_kind":"official","path":"avgen/evaluations/dists.py","file_url":"https://github.com/lzhangbj/ASVA/blob/HEAD/avgen/evaluations/dists.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dc842b5d99a54208"}},{"code_sha256_prefix":"4d6a7c69ebc8f61d","entry":"frechet_distance","repo":"lzhangbj/ASVA","repo_kind":"official","path":"avgen/evaluations/dists.py","file_url":"https://github.com/lzhangbj/ASVA/blob/HEAD/avgen/evaluations/dists.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4d6a7c69ebc8f61d"}},{"code_sha256_prefix":"aabcaf5e9e94e16a","entry":"get_model_size","repo":"lzhangbj/ASVA","repo_kind":"official","path":"avgen/utils.py","file_url":"https://github.com/lzhangbj/ASVA/blob/HEAD/avgen/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aabcaf5e9e94e16a"}},{"code_sha256_prefix":"f86dda815004b0b2","entry":"load_i3d_pretrained","repo":"lzhangbj/ASVA","repo_kind":"official","path":"avgen/evaluations/models/download.py","file_url":"https://github.com/lzhangbj/ASVA/blob/HEAD/avgen/evaluations/models/download.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f86dda815004b0b2"}},{"code_sha256_prefix":"0c6da1a913f23b47","entry":"random_compact_sample","repo":"lzhangbj/ASVA","repo_kind":"official","path":"avsync/data.py","file_url":"https://github.com/lzhangbj/ASVA/blob/HEAD/avsync/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0c6da1a913f23b47"}},{"code_sha256_prefix":"270cd726f1952c2a","entry":"timestep_embedding","repo":"lzhangbj/ASVA","repo_kind":"official","path":"avgen/evaluations/models/pytorch_i3d.py","file_url":"https://github.com/lzhangbj/ASVA/blob/HEAD/avgen/evaluations/models/pytorch_i3d.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"270cd726f1952c2a"}},{"code_sha256_prefix":"6e398d2ce9b196e4","entry":"trace_sqrt_product","repo":"lzhangbj/ASVA","repo_kind":"official","path":"avgen/evaluations/dists.py","file_url":"https://github.com/lzhangbj/ASVA/blob/HEAD/avgen/evaluations/dists.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6e398d2ce9b196e4"}},{"code_sha256_prefix":"1d3a3c2776d79f76","entry":"uniform_sample","repo":"lzhangbj/ASVA","repo_kind":"official","path":"avsync/data.py","file_url":"https://github.com/lzhangbj/ASVA/blob/HEAD/avsync/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1d3a3c2776d79f76"}},{"code_sha256_prefix":"9e65296ac68e0ab1","entry":"download","repo":"lzhangbj/ASVA","repo_kind":"official","path":"avgen/evaluations/models/download.py","file_url":"https://github.com/lzhangbj/ASVA/blob/HEAD/avgen/evaluations/models/download.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9e65296ac68e0ab1"}},{"code_sha256_prefix":"47cf0dd2012635a1","entry":"gather_tensor","repo":"lzhangbj/ASVA","repo_kind":"official","path":"avgen/utils.py","file_url":"https://github.com/lzhangbj/ASVA/blob/HEAD/avgen/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"47cf0dd2012635a1"}},{"code_sha256_prefix":"135b3dc835ffe6ad","entry":"get_confirm_token","repo":"lzhangbj/ASVA","repo_kind":"official","path":"avgen/evaluations/models/download.py","file_url":"https://github.com/lzhangbj/ASVA/blob/HEAD/avgen/evaluations/models/download.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"135b3dc835ffe6ad"}},{"code_sha256_prefix":"b6c9ff825741ff63","entry":"load_inceptionv3_pretrained","repo":"lzhangbj/ASVA","repo_kind":"official","path":"avgen/evaluations/models/inception_v3.py","file_url":"https://github.com/lzhangbj/ASVA/blob/HEAD/avgen/evaluations/models/inception_v3.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b6c9ff825741ff63"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}