{"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/discord-discrete-tokens-to-continuous-motion","title":"DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding","arxiv_id":"2411.19527","date":"2024-11-29","proceeding":null,"authors":["Jungbin Cho","Junwan Kim","Jisoo Kim","Minseo Kim","Mingu Kang","Sungeun Hong","Tae-Hyun Oh","Youngjae Yu"],"abstract":"Human motion is inherently continuous and dynamic, posing significant challenges for generative models. While discrete generation methods are widely used, they suffer from limited expressiveness and frame-wise noise artifacts. In contrast, continuous approaches produce smoother, more natural motion but often struggle to adhere to conditioning signals due to high-dimensional complexity and limited training data. To resolve this discord between discrete and continuous representations, we introduce DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding, a novel method that leverages rectified flow to decode discrete motion tokens in the continuous, raw motion space. Our core idea is to frame token decoding as a conditional generation task, ensuring that DisCoRD captures fine-grained dynamics and achieves smoother, more natural motions. Compatible with any discrete-based framework, our method enhances naturalness without compromising faithfulness to the conditioning signals on diverse settings. Extensive evaluations Our project page is available at: https://whwjdqls.github.io/discord.github.io/.","url_abs":"https://arxiv.org/abs/2411.19527v3","url_pdf":"https://arxiv.org/pdf/2411.19527v3.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":[],"tasks":[{"task_slug":"motion-synthesis","task_name":"Motion Synthesis"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/motion-synthesis-on-humanml3d","task":"Motion Synthesis","dataset":"HumanML3D","model":"DisCoRD (+MoMask)","rank_in_archive_order":4,"of":37,"metrics":{"FID":"0.032","Multimodality":"1.288","R Precision Top3":"0.809"},"uses_additional_data":false},{"leaderboard":"/sota/motion-synthesis-on-kit-motion-language","task":"Motion Synthesis","dataset":"KIT Motion-Language","model":"DisCoRD (+MoMask)","rank_in_archive_order":5,"of":31,"metrics":{"FID":"0.169","Multimodality":"1.266","R Precision Top3":"0.775"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.19527","atlas_url":"https://app.syntology.ai/?focus=2411.19527","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}