TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video Generation
Ruineng Li, Daitao Xing, Huiming Sun, Yuanzhou Ha, Jinglin Shen, Chiuman Ho
Abstract
A busy street scene with people walking T2V + Pose: A man working out at a gym T2V + Camera + Pose: A couple holding hands while walking on a beach I2V + Camera: A girl in a fashion flowing pink evening gown I2V + Pose: Woman in white sleeveless top with dark hair I2V + Camera + Pose: A musician in a yellow sweater standing next to a music
their joint interaction. We represent camera trajectories and human poses as spatio-temporal tokens to enable local control granularity. Our approach introduces a unified modeling framework utilizing a decouple-and-fuse strategy, bridged by a human-aware dynamic mask that effectively handles the spatially-and-temporally varying nature of combined motion signals. Through extensive experiments, we demonstrate TokenMotion's effectiveness across both text-to-video and image-to-video paradigms, consistently outperforming current state-of-the-art methods in human-centric motion control tasks. Our work represents a significant advancement in controllable video generation, with particular relevance for creative production applications.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
4 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Probabilistic Models
- High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Implicit Models
- Adding Conditional Control to Text-to-Image Diffusion Models cites High-Resolution Image Synthesis with Latent Diffusion Models
- Adding Conditional Control to Text-to-Image Diffusion Models cites Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
- VideoWorld 2: Learning Transferable Knowledge from Real-world Videos cites Adding Conditional Control to Text-to-Image Diffusion Models
- Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEs cites High-Resolution Image Synthesis with Latent Diffusion Models
- Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEs cites Denoising Diffusion Probabilistic Models
- Denoising Diffusion Implicit Models cites Denoising Diffusion Probabilistic Models
- Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites High-Resolution Image Synthesis with Latent Diffusion Models
- Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites Denoising Diffusion Probabilistic Models
- Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites Denoising Diffusion Implicit Models
Cited by top-tier papers4
- VideoWorld 2: Learning Transferable Knowledge from Real-world VideosZhongwei Ren, Yunchao Wei, Xiao Yu, Guixun Luo et al.CVPR 2026 · 9 citations
- O-DisCo-Edit: Object Distortion Control for Unified Realistic Video EditingYuqing Chen, Junjie Wang, Lin Liu, Ruihang Chu et al.AAAI 2026 · 6 citations
- AdaViewPlanner: Adapting Video Diffusion Models for Viewpoint Planning in 4D ScenesYu Li, Menghan Xia, Gongye Liu, Jianhong Bai et al.ICLR 2026 · 3 citations
- Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEsSicheng Xu, Yu Deng, Shoukang Hu, Yichuan Wang et al.CVPR 2026 · 1 citation
Builds on23
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 11,743 citations
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li et al.NeurIPS 2022 · 8,965 citations
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 6,759 citations
Related papers
- RealisMotion: Decomposed Human Motion Control and Video Generation in the World SpaceJingyun Liang, Jingkai Zhou, Shikai Li, Chenjie Cao et al.ICML 2026 · 9 citations
- MoSA: Motion-Coherent Human Video Generation via Structure-Appearance DecouplingHaoyu Wang, Hao Tang, Donglin Di, Zhilu Zhang et al.ICLR 2026 · 4 citations
- TGT: Text-Grounded Trajectories for Locally Controlled Video GenerationGuofeng Zhang, Angtian Wang, Jacob Zhiyuan Fang, Liming Jiang et al.CVPR 2026 · 5 citations
- Mask2IV: Interaction-Centric Video Generation via Mask TrajectoriesGen Li, Bo Zhao, Jianfei Yang, Laura Sevilla-LaraAAAI 2026 · 6 citations
- I2VControl: Disentangled and Unified Video Motion Synthesis ControlWanquan Feng, Tianhao Qi, Jiawei Liu, Mingzhen Sun et al.ICCV 2025
