{"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/ldmvfi-video-frame-interpolation-with-latent","title":"LDMVFI: Video Frame Interpolation with Latent Diffusion Models","arxiv_id":"2303.09508","date":"2023-03-16","proceeding":null,"authors":["Duolikun Danier","Fan Zhang","David Bull"],"abstract":"Existing works on video frame interpolation (VFI) mostly employ deep neural networks that are trained by minimizing the L1, L2, or deep feature space distance (e.g. VGG loss) between their outputs and ground-truth frames. However, recent works have shown that these metrics are poor indicators of perceptual VFI quality. Towards developing perceptually-oriented VFI methods, in this work we propose latent diffusion model-based VFI, LDMVFI. This approaches the VFI problem from a generative perspective by formulating it as a conditional generation problem. As the first effort to address VFI using latent diffusion models, we rigorously benchmark our method on common test sets used in the existing VFI literature. Our quantitative experiments and user study indicate that LDMVFI is able to interpolate video content with favorable perceptual quality compared to the state of the art, even in the high-resolution regime. Our code is available at https://github.com/danier97/LDMVFI.","url_abs":"https://arxiv.org/abs/2303.09508v3","url_pdf":"https://arxiv.org/pdf/2303.09508v3.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":"ldmvfi-video-frame-interpolation-with-latent","repo_url":"https://github.com/danielism97/ldmvfi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"ldmvfi-video-frame-interpolation-with-latent","repo_url":"https://github.com/danier97/ldmvfi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"video-frame-interpolation","task_name":"Video Frame Interpolation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.09508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09508"}},"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/danielism97/ldmvfi","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/danier97/ldmvfi","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_violates":2,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":11,"ran":7,"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":"9e8e56135365289e","entry":"CharbonnierFunc","repo":"danielism97/ldmvfi","repo_kind":"official","path":"utility.py","file_url":"https://github.com/danielism97/ldmvfi/blob/HEAD/utility.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9e8e56135365289e"}},{"code_sha256_prefix":"424012cb37b31172","entry":"default","repo":"danielism97/ldmvfi","repo_kind":"official","path":"ldm/modules/attention.py","file_url":"https://github.com/danielism97/ldmvfi/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"424012cb37b31172"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"danielism97/ldmvfi","repo_kind":"official","path":"ldm/modules/attention.py","file_url":"https://github.com/danielism97/ldmvfi/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"b1368330cf0f5642","entry":"isimage","repo":"danielism97/ldmvfi","repo_kind":"official","path":"ldm/util.py","file_url":"https://github.com/danielism97/ldmvfi/blob/HEAD/ldm/util.py","link_basis":"harvester_set","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":"b1368330cf0f5642"}},{"code_sha256_prefix":"d72762b700feee6f","entry":"ismap","repo":"danielism97/ldmvfi","repo_kind":"official","path":"ldm/util.py","file_url":"https://github.com/danielism97/ldmvfi/blob/HEAD/ldm/util.py","link_basis":"harvester_set","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":"d72762b700feee6f"}},{"code_sha256_prefix":"9a2082456dfd29d9","entry":"moduleNormalize","repo":"danielism97/ldmvfi","repo_kind":"official","path":"utility.py","file_url":"https://github.com/danielism97/ldmvfi/blob/HEAD/utility.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9a2082456dfd29d9"}},{"code_sha256_prefix":"9a299fe5ae09e407","entry":"uniq","repo":"danielism97/ldmvfi","repo_kind":"official","path":"ldm/modules/attention.py","file_url":"https://github.com/danielism97/ldmvfi/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9a299fe5ae09e407"}},{"code_sha256_prefix":"77053422accd9567","entry":"MBConv","repo":"danielism97/ldmvfi","repo_kind":"official","path":"ldm/modules/maxvit.py","file_url":"https://github.com/danielism97/ldmvfi/blob/HEAD/ldm/modules/maxvit.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":"77053422accd9567"}},{"code_sha256_prefix":"50fe0d31f1836940","entry":"cupy_kernel","repo":"danielism97/ldmvfi","repo_kind":"official","path":"cupy_module/dsepconv.py","file_url":"https://github.com/danielism97/ldmvfi/blob/HEAD/cupy_module/dsepconv.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":"50fe0d31f1836940"}},{"code_sha256_prefix":"f9bd2e83191afad1","entry":"log_txt_as_img","repo":"danielism97/ldmvfi","repo_kind":"official","path":"ldm/util.py","file_url":"https://github.com/danielism97/ldmvfi/blob/HEAD/ldm/util.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":"f9bd2e83191afad1"}},{"code_sha256_prefix":"6ca8b7ed416e3f32","entry":"read_frame_yuv2rgb","repo":"danielism97/ldmvfi","repo_kind":"official","path":"utility.py","file_url":"https://github.com/danielism97/ldmvfi/blob/HEAD/utility.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":"6ca8b7ed416e3f32"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}