{"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/a-dynamic-multi-scale-voxel-flow-network-for","title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","arxiv_id":"2303.09875","date":"2023-03-17","proceeding":"CVPR 2023 1","authors":["Xiaotao Hu","Zhewei Huang","Ailin Huang","Jun Xu","Shuchang Zhou"],"abstract":"The performance of video prediction has been greatly boosted by advanced deep neural networks. However, most of the current methods suffer from large model sizes and require extra inputs, e.g., semantic/depth maps, for promising performance. For efficiency consideration, in this paper, we propose a Dynamic Multi-scale Voxel Flow Network (DMVFN) to achieve better video prediction performance at lower computational costs with only RGB images, than previous methods. The core of our DMVFN is a differentiable routing module that can effectively perceive the motion scales of video frames. Once trained, our DMVFN selects adaptive sub-networks for different inputs at the inference stage. Experiments on several benchmarks demonstrate that our DMVFN is an order of magnitude faster than Deep Voxel Flow and surpasses the state-of-the-art iterative-based OPT on generated image quality. Our code and demo are available at https://huxiaotaostasy.github.io/DMVFN/.","url_abs":"https://arxiv.org/abs/2303.09875v2","url_pdf":"https://arxiv.org/pdf/2303.09875v2.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":"a-dynamic-multi-scale-voxel-flow-network-for","repo_url":"https://github.com/megvii-research/CVPR2023-DMVFN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"video-prediction","task_name":"Video Prediction"}],"methods":[{"method_slug":"dmvfn","method_name":"DMVFN"},{"method_slug":"opt","method_name":"OPT"}],"datasets_introduced":[],"methods_introduced":[{"slug":"dmvfn","name":"DMVFN","full_name":"A Dynamic Multi-Scale Voxel Flow Network"}],"results":[{"leaderboard":"/sota/video-prediction-on-cityscapes-1","task":"Video Prediction","dataset":"Cityscapes","model":"DMVFN","rank_in_archive_order":1,"of":3,"metrics":{"LPIPS":"0.0558","MS-SSIM":"0.9573"},"uses_additional_data":false},{"leaderboard":"/sota/video-prediction-on-davis-2017","task":"Video Prediction","dataset":"DAVIS 2017","model":"DMVFN","rank_in_archive_order":1,"of":2,"metrics":{"LPIPS":"0.0996","MS-SSIM":"0.8397"},"uses_additional_data":false},{"leaderboard":"/sota/video-prediction-on-kitti","task":"Video Prediction","dataset":"KITTI","model":"DMVFN","rank_in_archive_order":1,"of":3,"metrics":{"LPIPS":"0.1074","MS-SSIM":"0.8853"},"uses_additional_data":false},{"leaderboard":"/sota/video-prediction-on-vimeo90k","task":"Video Prediction","dataset":"Vimeo90K","model":"DMVFN","rank_in_archive_order":2,"of":3,"metrics":{"LPIPS":"0.0369","MS-SSIM":"0.9701"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.09875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09875"}},"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/megvii-research/CVPR2023-DMVFN","reach":null}],"summary":{"ran":2,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":"2b15709b0e8bffb8","entry":"MVFB","repo":"megvii-research/CVPR2023-DMVFN","repo_kind":"official","path":"model/arch.py","file_url":"https://github.com/megvii-research/CVPR2023-DMVFN/blob/HEAD/model/arch.py","link_basis":"first_harvest_node","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":"2b15709b0e8bffb8"}},{"code_sha256_prefix":"44216cabdd941590","entry":"RoundSTE","repo":"megvii-research/CVPR2023-DMVFN","repo_kind":"official","path":"model/arch.py","file_url":"https://github.com/megvii-research/CVPR2023-DMVFN/blob/HEAD/model/arch.py","link_basis":"first_harvest_node","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":"44216cabdd941590"}},{"code_sha256_prefix":"8a3307b80dfb6871","entry":"warp","repo":"megvii-research/CVPR2023-DMVFN","repo_kind":"official","path":"model/arch.py","file_url":"https://github.com/megvii-research/CVPR2023-DMVFN/blob/HEAD/model/arch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8a3307b80dfb6871"}},{"code_sha256_prefix":"d521cc2d3ec89658","entry":"DMVFN","repo":"megvii-research/CVPR2023-DMVFN","repo_kind":"official","path":"model/arch.py","file_url":"https://github.com/megvii-research/CVPR2023-DMVFN/blob/HEAD/model/arch.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":"d521cc2d3ec89658"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}