{"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/hearing-anything-anywhere","title":"Hearing Anything Anywhere","arxiv_id":"2406.07532","date":"2024-06-11","proceeding":"CVPR 2024 1","authors":["Mason Wang","Ryosuke Sawata","Samuel Clarke","Ruohan Gao","Shangzhe Wu","Jiajun Wu"],"abstract":"Recent years have seen immense progress in 3D computer vision and computer graphics, with emerging tools that can virtualize real-world 3D environments for numerous Mixed Reality (XR) applications. However, alongside immersive visual experiences, immersive auditory experiences are equally vital to our holistic perception of an environment. In this paper, we aim to reconstruct the spatial acoustic characteristics of an arbitrary environment given only a sparse set of (roughly 12) room impulse response (RIR) recordings and a planar reconstruction of the scene, a setup that is easily achievable by ordinary users. To this end, we introduce DiffRIR, a differentiable RIR rendering framework with interpretable parametric models of salient acoustic features of the scene, including sound source directivity and surface reflectivity. This allows us to synthesize novel auditory experiences through the space with any source audio. To evaluate our method, we collect a dataset of RIR recordings and music in four diverse, real environments. We show that our model outperforms state-ofthe-art baselines on rendering monaural and binaural RIRs and music at unseen locations, and learns physically interpretable parameters characterizing acoustic properties of the sound source and surfaces in the scene.","url_abs":"https://arxiv.org/abs/2406.07532v1","url_pdf":"https://arxiv.org/pdf/2406.07532v1.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":"hearing-anything-anywhere","repo_url":"https://github.com/maswang32/hearinganythinganywhere","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"mixed-reality","task_name":"Mixed Reality"},{"task_slug":"room-impulse-response-rir","task_name":"Room Impulse Response (RIR)"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.07532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07532"}},"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/maswang32/hearinganythinganywhere","reach":{"status":"ok"}}],"summary":{"ran":9,"unverified":3},"by_repo_kind":{"official":{"samples":12,"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":12,"samples":[{"code_sha256_prefix":"2df25329fdac5195","entry":"L1_and_Log","repo":"maswang32/hearinganythinganywhere","repo_kind":"official","path":"metrics.py","file_url":"https://github.com/maswang32/hearinganythinganywhere/blob/HEAD/metrics.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":"2df25329fdac5195"}},{"code_sha256_prefix":"655bbc152fb88d7f","entry":"compute_barycentric","repo":"maswang32/hearinganythinganywhere","repo_kind":"official","path":"trace.py","file_url":"https://github.com/maswang32/hearinganythinganywhere/blob/HEAD/trace.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":"655bbc152fb88d7f"}},{"code_sha256_prefix":"0655fda4c828e27d","entry":"compute_complement_indices","repo":"maswang32/hearinganythinganywhere","repo_kind":"official","path":"rooms/dataset.py","file_url":"https://github.com/maswang32/hearinganythinganywhere/blob/HEAD/rooms/dataset.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":"0655fda4c828e27d"}},{"code_sha256_prefix":"445455cc5eec3fc3","entry":"compute_error","repo":"maswang32/hearinganythinganywhere","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/maswang32/hearinganythinganywhere/blob/HEAD/evaluate.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":"445455cc5eec3fc3"}},{"code_sha256_prefix":"8ea2a0878e2361fc","entry":"eval_music","repo":"maswang32/hearinganythinganywhere","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/maswang32/hearinganythinganywhere/blob/HEAD/evaluate.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":"8ea2a0878e2361fc"}},{"code_sha256_prefix":"889d31915dcf82d4","entry":"gen_counts","repo":"maswang32/hearinganythinganywhere","repo_kind":"official","path":"render.py","file_url":"https://github.com/maswang32/hearinganythinganywhere/blob/HEAD/render.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":"889d31915dcf82d4"}},{"code_sha256_prefix":"d71f3648d8c1faf9","entry":"get_stft","repo":"maswang32/hearinganythinganywhere","repo_kind":"official","path":"metrics.py","file_url":"https://github.com/maswang32/hearinganythinganywhere/blob/HEAD/metrics.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":"d71f3648d8c1faf9"}},{"code_sha256_prefix":"eb563053805b7bb2","entry":"line_surface_intersect","repo":"maswang32/hearinganythinganywhere","repo_kind":"official","path":"trace.py","file_url":"https://github.com/maswang32/hearinganythinganywhere/blob/HEAD/trace.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":"eb563053805b7bb2"}},{"code_sha256_prefix":"b218c35ae77c76b2","entry":"safe_log","repo":"maswang32/hearinganythinganywhere","repo_kind":"official","path":"metrics.py","file_url":"https://github.com/maswang32/hearinganythinganywhere/blob/HEAD/metrics.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":"b218c35ae77c76b2"}},{"code_sha256_prefix":"7bf7d47d4f46d966","entry":"dataLoader","repo":"maswang32/hearinganythinganywhere","repo_kind":"official","path":"rooms/dataset.py","file_url":"https://github.com/maswang32/hearinganythinganywhere/blob/HEAD/rooms/dataset.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":"7bf7d47d4f46d966"}},{"code_sha256_prefix":"4dff39410d55102a","entry":"get_interpolator","repo":"maswang32/hearinganythinganywhere","repo_kind":"official","path":"render.py","file_url":"https://github.com/maswang32/hearinganythinganywhere/blob/HEAD/render.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":"4dff39410d55102a"}},{"code_sha256_prefix":"c4713a8415a1bc12","entry":"get_listener","repo":"maswang32/hearinganythinganywhere","repo_kind":"official","path":"render.py","file_url":"https://github.com/maswang32/hearinganythinganywhere/blob/HEAD/render.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":"c4713a8415a1bc12"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}