Human Motion and Animation

Últimos artículos

• Eulerian Motion Reconstruction for Water Scenery

  Chuhan Chen, Yen-Chi Cheng, Ayush Saraf, Rajvi Shah, Tuotuo Li, Johannes Kopf, Chen Gao, Hung-Yu Tseng, Deva Ramanan, Matthew O'Toole, Changil Kim · 1 de octubre de 2026

  Reconstructing and animating water scenery from nature produces compelling and immersive visual experiences. Previous work examined this task from the perspective of 2D video textures, with the goal of creating a looping video. In our work, we tackle the problem from a 3D perspective, creating a loo…

• PAMI: Part Anchored Motion for Text to Human-Object Interaction Generation

  Chuqiao Li, Xianghui Xie, Yong Cao, Andreas Geiger, Gerard Pons-Moll · 1 de octubre de 2026

  Text-conditioned full-body human-object interaction (HOI) generation requires synthesizing human motion and object trajectories that match the input text while remaining precisely coordinated over time. Most methods represent the human and object as separate trajectories and predict the global human…

• Strike a Chord! Modal Kinetic Typography

  Maham Tanveer, Jiyeon Han, Nanxuan Zhao, Hao Zhang · 1 de octubre de 2026

  We introduce modal kinetic typography, which animates a vector glyph to express a semantic concept while keeping it legible. Our key idea is to build motion from the glyph's natural vibration modes. Specifically, a finite-element eigenproblem assembled from the vector outline yields the glyph's soft…

• DiffWAM: A Fast and Efficient Navigation World Action Model

  Mo Zhu, Yuze Wu, Xijie Huang, Xiao Cui, Fei Gao, Xin Zhou · 1 de octubre de 2026

  Pretrained video foundation models encode rich semantic and spatiotemporal priors for embodied navigation, yet converting these priors into UAV motion typically requires expensive future-video synthesis and geometric reconstruction. We investigate whether the motion implicit in future visual predict…

• ECHO-G: Embodied Co-speech Humanoid mOtion Generation

  Yizhao Li, Pusen Gao, Ming Wang, Shaojie Shen, Shuo Yang, Hao Xu · 1 de octubre de 2026

  Generating full-body co-speech motion for humanoid robots requires coordinating speech prosody, linguistic content, and embodiment-specific motion. To this end, we present ECHO-G, a framework jointly conditioned on speech audio and timed transcripts. Its Speech-Grounded Diffusion Transformer (SGDiT)…

• Unveiling the Value of Motion for Cinematic Camera Trajectories

  Ziqi Zhou, Yujian Yuan, Laura Sevilla-Lara · 1 de octubre de 2026

  Cinematic camera motion is a fundamental storytelling tool, defined not only by where the camera is positioned in the scene, but also by how it moves in terms of direction and speed. Recent work on camera trajectory generation and alignment to text relies on pose-centric representations. While in pr…

• Retargeting Motions to Diverse Skeletons via Learnable Flattening

  Kia-J\"ung Yang, Fabian H. Sinz, Pawe{\l} A. Pierzchlewicz · 1 de octubre de 2026

  Cross-structural motion retargeting aims to transfer motion between different skeletal topologies. Despite recent progress, existing state-of-the-art models struggle with reliability in zero-shot settings, i.e. skeletons with different topologies which were unseen during training, and recent Transfo…

• MotionInsight: Diagnosing Object Motion Deficiencies in Generated Videos

  Jiahao Zhan, Yongrui Ma, Qunliang Xing, Xuanyu Zhang, Jingqi Tong, Junlin Li, Li zhang, Shijie Zhao, Tianfan Xue · 30 de septiembre de 2026

  Despite rapid progress in video generation models, they still exhibit obvious motion deficiencies, often manifested as incorrect object motion. However, most existing video quality evaluations focus on aesthetic quality or text-video alignment. To address this gap, we study object-centric motion fid…

• WeLike2Party! In-Context Motion Transfer for Multi-Human Image Animation

  Sangeyl Lee, Seunghyun Shin, Seungho Park, Wooseok Jeon, Hae-Gon Jeon · 30 de septiembre de 2026

  Human image animation aims to transfer motion from a driving video to subjects in a reference image. Despite remarkable progress in video generation, achieving high-fidelity animation of multiple interacting subjects remains a challenge. Many existing approaches rely on explicit motion representatio…

• Text2Sim: Agentic Physics-Based Simulation Generation with Distilled Expertise

  Xiaoyu Xiong, Tsun-Hsuan Wang, Yi-Ling Qiao, Tao Du, Minchen Li · 30 de septiembre de 2026

  Creating diverse physical simulations remains labor-intensive because assets, layout, physical parameters, motion, control, and rendering must be designed and debugged jointly. We present Text2Sim, a simulation-specialized agentic pipeline that converts a text-only request into an executable, editab…

• Generative Interactions: Weaving Multiparty Human Motion with Bilevel Latent Dynamics

  Ojas Shirekar, Yash Surange, Agustinas Ju\v{c}as, Chirag Raman · 30 de septiembre de 2026

  Human social behaviour is not a collection of independent motions, but a jointly organised process in which group dynamics and individual variation continuously shape one another. Yet existing social motion models often prioritise plausible trajectories while leaving interaction state implicit, limi…

• DualTrack: Synchronized speech-gesture generation via symmetric coupling of pretrained priors

  Yuanzhuo Hu, Zehan Liu, Xiaoyi Qin, Ming Li · 30 de septiembre de 2026

  Joint speech-gesture synthesis must coordinate two modalities despite limited paired data. Existing approaches often lack bidirectional interaction, have limited language coverage, or simplify body and finger representations. We present DualTrack, which couples pretrained speech and motion priors on…

• Harnessing Coupled Stream Completion For Human-Object Ineraction Modeling

  Dawei Guan, Di Yang, Jiangtao Wang · 29 de septiembre de 2026

  Text-conditioned human-object interaction (HOI) generation requires body motion, object trajectories & rotations, and hand articulation to remain coordinated. These components differ in scale and dynamics, but must agree on contact, relative pose, and timing. A shared representation may limit the di…

• ReFM: Semantic-Aware Refinement Flow Model for Motion Retargeting

  Jingxiang Qu, Lucie Taglienti, Evan Atherton · 29 de septiembre de 2026

  Motion retargeting transfers motion across characters with different skeletal structures while preserving semantic intent and physical plausibility. Despite recent progress, two fundamental questions remain: (i) how can reliable source-motion semantics be learned without high-quality paired retarget…

• OSPO: Object-Centric Self-Improving Preference Optimization for Text-to-Image Generation

  Yoonjin Oh, Yongjin Kim, Hyomin Kim, Donghwan Chi, Sungwoong Kim · 28 de septiembre de 2026

  Recent advances in Multimodal Large Language Models (MLLMs) have enabled unified multimodal understanding and generation. However, they still struggle with fine-grained text-image alignment, often failing to faithfully depict objects with correct attributes such as color, shape, and spatial relation…

• Motion Style Slider: Endpoint-Supervised Continuous Style Control for Human Motion Diffusion

  Chen-Chieh Liao, Yichen Peng, Yiyi Cai, Y\^ui Ono, Hiroki Hanaoka, Erwin Wu, Hideki Koike, Shuichi Kurabayashi · 28 de septiembre de 2026

  Existing human motion diffusion methods provide strong motion generation quality, and recent style transfer models can inject target style cues, but fine-grained continuous control of style intensity remains underexplored. In production, style intensity is subjective across artists and directors, so…

• Timo: $\textbf{T}$aming Mult$\textbf{i}$modal Diffusion Transformer for Human $\textbf{Mo}$tion Generation

  Zhao Wang, Jiangtao Hu, Jack Yu, Tao Yu · 28 de septiembre de 2026

  Most existing human motion generation (HMG) methods use cross-attention modules to inject text semantics, but ignore the importance of bidirectional modeling between motion and text tokens, which limits text comprehension. A straightforward idea is introducing multimodal diffusion transformers (MMDi…

• DyMD: Preserving Interaction Dynamics through Distribution Matching Distillation in Few-Step Video World Models

  Haojun Xu, Jie Huang, Xin Lu, Mingchen Zhong, Zihao Fan, Linjiang Huang, Si Liu · 28 de septiembre de 2026

  Large video diffusion models offer expressive priors for embodied prediction and learning, yet their many-step sampling remains costly for interactive downstream use. Distribution Matching Distillation (DMD) enables few-step video generation, but can suppress robot--object motion while preserving vi…

• OneWorld: Learning Consistent Physics Across Actions in World Models

  Ke He, Yichen Ding, Bin Yang · 28 de septiembre de 2026

  Action-conditioned video world models aim to predict scene evolution under different actions, a capability that is essential for reliable planning, decision-making, and interaction in dynamic environments. However, futures generated independently from the same initial scene may each appear plausible…

• BeyondRetarget: Learning Executable Humanoid Motions Directly from Monocular Video

  Tianyu Xiong, Yi Lu, Jinrui Wang, Ziqi Liang, Dandan Lei, Xiaoyang Zhou, Xiao-xiao Long, Qiu Shen, Xun Cao · 25 de septiembre de 2026

  Learning executable motions from human videos offers a scalable solution for humanoid robots to acquire demonstration motions. However, existing pipelines typically first construct an explicit human motion representation and then convert it into robot motions via motion retargeting. Although such me…

• Frozen Flows Forget: Diagnosing and Restoring Lost Motion in a Latent-flow World Model

  Xiwen Chen, Rigaudiere Z. Li, Zhiruo Zhou, Xiaojun Zhu, Houde Liu · 24 de septiembre de 2026

  Latent world models that integrate a flow in a frozen self supervised latent space train stably and cheaply, yet silently lose the property manipulation depends on most: motion. The pretrained flow never moves the manipulated object; retraining it with latent-only losses only trades stillness for te…

• MotionSpec: Spectral Trajectory Supervision for Motion-Consistent Video Generation

  Ziqi Ni, Rui Li, Shiqi Jiang, Wei Zhou · 24 de septiembre de 2026

  Recent advances in text-to-video generation have enabled high-fidelity visual synthesis, yet realistic motion remains challenging. Generated videos may exhibit temporal discontinuities, inconsistent action progression, and structural distortions during complex movements. Even when individual frames …

• MoSAT: Human Motion Generation from Spatial Audio and Textual Description

  Shuyang Xu, Zhiyang Dou, Yiduo Hao, Zekun Li, Liang Pan, Jingbo Wang, Cheng Lin, Yuan Liu, Wenping Wang, Mingmin Zhao, Taku Komura · 22 de septiembre de 2026

  Human motion is shaped by both external acoustic events and behavioral intent: spatial audio conveys environmental cues that elicit or guide a response, while text specifies the desired action and how it should be performed. In this paper, we study the novel task of human motion synthesis jointly co…

• NeuIDO: Neural Intrinsic Dynamics Operator for Physics-Informed 4D World Models

  Jiajing Lin, Xin Zhang, Jianhua Sun · 22 de septiembre de 2026

  World models aim to capture environmental dynamics and predict future trajectories, showing growing potential for embodied intelligence. Physics-informed 4D generation integrates physical simulation to predict 3D object interactions, offering a promising pathway toward world models. However, this pa…

• CoaG: Cylinders on a Grid: Coarse 3D Layout Control for Video Generation

  Zhangsihao Yang, Mengyi Shan · 22 de septiembre de 2026

  We ask how little geometry a person has to draw to control both where people stand and where the camera moves in a generated video. Our answer is a ground plane and one cylinder per person. A user draws a grid on the ground, places one cylinder where each person should stand, moves the cylinders and…