{"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/super-slomo-high-quality-estimation-of","title":"Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation","arxiv_id":"1712.00080","date":"2017-11-30","proceeding":"CVPR 2018 6","authors":["Huaizu Jiang","Deqing Sun","Varun Jampani","Ming-Hsuan Yang","Erik Learned-Miller","Jan Kautz"],"abstract":"Given two consecutive frames, video interpolation aims at generating\nintermediate frame(s) to form both spatially and temporally coherent video\nsequences. While most existing methods focus on single-frame interpolation, we\npropose an end-to-end convolutional neural network for variable-length\nmulti-frame video interpolation, where the motion interpretation and occlusion\nreasoning are jointly modeled. We start by computing bi-directional optical\nflow between the input images using a U-Net architecture. These flows are then\nlinearly combined at each time step to approximate the intermediate\nbi-directional optical flows. These approximate flows, however, only work well\nin locally smooth regions and produce artifacts around motion boundaries. To\naddress this shortcoming, we employ another U-Net to refine the approximated\nflow and also predict soft visibility maps. Finally, the two input images are\nwarped and linearly fused to form each intermediate frame. By applying the\nvisibility maps to the warped images before fusion, we exclude the contribution\nof occluded pixels to the interpolated intermediate frame to avoid artifacts.\nSince none of our learned network parameters are time-dependent, our approach\nis able to produce as many intermediate frames as needed. We use 1,132 video\nclips with 240-fps, containing 300K individual video frames, to train our\nnetwork. Experimental results on several datasets, predicting different numbers\nof interpolated frames, demonstrate that our approach performs consistently\nbetter than existing methods.","url_abs":"http://arxiv.org/abs/1712.00080v2","url_pdf":"http://arxiv.org/pdf/1712.00080v2.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":"super-slomo-high-quality-estimation-of","repo_url":"https://github.com/NVIDIA/unsupervised-video-interpolation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"super-slomo-high-quality-estimation-of","repo_url":"https://github.com/avinashpaliwal/Super-SloMo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"super-slomo-high-quality-estimation-of","repo_url":"https://github.com/manastahir/Nvidia--SuperSlowMo-Keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"super-slomo-high-quality-estimation-of","repo_url":"https://github.com/rmalav15/Super-SloMo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"super-slomo-high-quality-estimation-of","repo_url":"https://github.com/susomena/DeepSlowMotion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"video-frame-interpolation","task_name":"Video Frame Interpolation"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-frame-interpolation-on-msu-video-frame","task":"Video Frame Interpolation","dataset":"MSU Video Frame Interpolation","model":"Super-SloMo","rank_in_archive_order":3,"of":24,"metrics":{"FPS":"3.1","LPIPS":"0.068","MS-SSIM":"0.924","PSNR":"26.69","SSIM":"0.904","Subjective score":"1.11","VMAF":"61.35"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1712.00080","atlas_url":"https://app.syntology.ai/?focus=1712.00080","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.00080"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/susomena/DeepSlowMotion","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rmalav15/Super-SloMo","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/manastahir/Nvidia--SuperSlowMo-Keras","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NVIDIA/unsupervised-video-interpolation","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/avinashpaliwal/Super-SloMo","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"listed":{"samples":2,"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":"f220725a8c1b4e18","entry":"extract_frames","repo":"avinashpaliwal/Super-SloMo","repo_kind":"listed","path":"video_to_slomo.py","file_url":"https://github.com/avinashpaliwal/Super-SloMo/blob/HEAD/video_to_slomo.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f220725a8c1b4e18"}},{"code_sha256_prefix":"41bbbfc4c64e2f36","entry":"create_video","repo":"avinashpaliwal/Super-SloMo","repo_kind":"listed","path":"video_to_slomo.py","file_url":"https://github.com/avinashpaliwal/Super-SloMo/blob/HEAD/video_to_slomo.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":"41bbbfc4c64e2f36"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}