{"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/motion-inbetweening-via-deep-d-interpolator","title":"Motion Inbetweening via Deep $Δ$-Interpolator","arxiv_id":"2201.06701","date":"2022-01-18","proceeding":null,"authors":["Boris N. Oreshkin","Antonios Valkanas","Félix G. Harvey","Louis-Simon Ménard","Florent Bocquelet","Mark J. Coates"],"abstract":"We show that the task of synthesizing human motion conditioned on a set of key frames can be solved more accurately and effectively if a deep learning based interpolator operates in the delta mode using the spherical linear interpolator as a baseline. We empirically demonstrate the strength of our approach on publicly available datasets achieving state-of-the-art performance. We further generalize these results by showing that the $\\Delta$-regime is viable with respect to the reference of the last known frame (also known as the zero-velocity model). This supports the more general conclusion that operating in the reference frame local to input frames is more accurate and robust than in the global (world) reference frame advocated in previous work. Our code is publicly available at https://github.com/boreshkinai/delta-interpolator.","url_abs":"https://arxiv.org/abs/2201.06701v4","url_pdf":"https://arxiv.org/pdf/2201.06701v4.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":"motion-inbetweening-via-deep-d-interpolator","repo_url":"https://github.com/boreshkinai/delta-interpolator","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"motion-synthesis","task_name":"Motion Synthesis"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/motion-synthesis-on-lafan1","task":"Motion Synthesis","dataset":"LaFAN1","model":"$\\Delta$-interpolator","rank_in_archive_order":1,"of":4,"metrics":{"L2P@15":"0.47","L2P@30":"1.00","L2P@5":"0.13","L2Q@15":"0.32","L2Q@30":"0.57","L2Q@5":"0.11","NPSS@15":"0.0217","NPSS@30":"0.1217","NPSS@5":"0.0014"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2201.06701","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}