3D Motion

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 31

All topics

Generative Cinematographer: Composing Camera and Object Motion in 3D
Oct 1, 2026Jiahan Zhang, Chaohao Yang, Namitha Guruprasad +43D Motion Camera Control
Johns Hopkins University
4Director: Controlling Video World Models with Rigid 3D Geometry
Oct 1, 2026Wei Cao, Hao Zhang, Vikram Voleti +53D Motion Video World Models
Stability AI · University of Illinois Urbana-Champaign
Eulerian Motion Reconstruction for Water Scenery
Sep 29, 2026Chuhan Chen, Yen-Chi Cheng, Ayush Saraf +84D Reconstruction 3D Motion
Carnegie Mellon University · University of Illinois Urbana-Champaign · Meta
World2Motion: Turning Video World Models into 3D Human Motion Generators
Sep 29, 2026Fangyuan Tu, Xiangyue Zhang, Yiyi Cai +83D Motion Video World Models
Japan Advanced Institute of Science and Technology · The University of Tokyo · Institute of Science Tokyo +1
PointZero: 3D Point Track Completion for Learning Transferable 3D Dynamics
Sep 16, 2026Bardienus P. Duisterhof, Kaifeng Zhang, Adam Hung +53D Tracking 3D Scene Understanding
CMU · Columbia · NVIDIA
Dyn-3D: Unveiling and Resolving Ego-Motion Ambiguity in Vision-Language Models
Sep 1, 2026Jiayu Ding, Zhuodong Liu, Lei Zhang +63D Spatial Reasoning 3D Motion
InkMind Team
StreamTalk: Streaming Co-Speech Gesture Generation with Key-Pose Anchoring
Aug 3, 2026Xiangyue Zhang, Jianfang Li, Jiaxu Zhang +2Co-Speech Gesture Generation Audio-Video Generation
The University of Tokyo · Alibaba Group · Nanyang Technological University +1
HarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction Synthesis
Jul 19, 2026Lingwei Dang, Juntong Li, Zonghan Li +5Hand-Object Interaction Detection 3D Motion
South China University of Technology, Guangzhou, China · Beijing Normal University, Beijing, China · Tsinghua University, Beijing, China +1
PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation
Jul 2, 2026Peng Yun, Shouwang Huang, Hao Li +3Efficient World-Action Model 3D World
vLAR Group, The Hong Kong Polytechnic University, Hong Kong SAR, China · Astribot, China
World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video
Jul 1, 2026Liyuan Zhu, Shengyu Huang, Amrita Mazumdar +6Monocular Video 4D Reconstruction
1Stanford University · 2NVIDIA
3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement
Jun 29, 2026Deyin Liu, Jicheng Xu, Lin Yuanbo Wu +43D Motion Camera Trajectories
Engineering Research Center of Autonomous Unmanned System Technology, Ministry of Education; Anhui Provincial Key Laboratory of Security Artificial Intelligence; and School of Artificial Intelligence, Anhui University, Hefei, China · University of Surrey, Guildford, United Kingdom · University of Warwick, Coventry, United Kingdom +1
PhysiFormer: Learning to Simulate Mechanics in World Space
Jun 25, 2026Yiming Chen, Yushi Lan, Andrea VedaldiPhysics Simulation 3D Motion
Visual Geometry Group, University of Oxford
Neural Voxel Dynamics: Learning Implicit 3D Physics via Volumetric Feature Advection
Jun 24, 2026Zican Wang, Niloy Mitra3D Motion Volume
University College London · Adobe Research
Social Structure Matters in 3D Human-Human Interaction Generation
Jun 23, 2026Zhongju Wang, Beier Wang, Yatao Bian +6Human Motion Generation Articulated Objects
University of New South Wales · National University of Singapore · NVIDIA +3
4DVLT: Dynamic Scene Understanding with Worldline-Centered Vision-Language Tracking
Jun 21, 2026Chaoyue Li, Boxue Yang, Shengyao Zhou +33D Motion Scene Understanding
Huazhong University of Science and Technology · Shanghai Jiao Tong University · Zhejiang University
MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction
Jun 17, 2026Jianing Zhang, Chenhao Zheng, Yajun Yang +10Human Motion Prediction 3D Motion
1Allen Institute for AI · University of Washington · 3UNC-Chapel Hill
FLAP: FOV-Constrained Active Perception Planning for Prior-Map-Free 3D Navigation
Jun 16, 2026Mengke Zhang, Sitong Li, Tiancheng Lai +6Unmanned Aerial Vehicle Trajectories Viewpoint-Dependent Active Perception
The State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China. · Huzhou Institute, Zhejiang University, and Huzhou Key Laboratory of Autonomous System, Huzhou 313000, China. · Shanghai Institute of Special Equipment Inspection and Technical Research Co., Ltd, Shanghai 200062, China.
PhysAgent: Automating Physics-Based 4D Synthesis via Trajectory-Grounded Multi-Agent Feedback
Jun 7, 2026Chunji Lv, Jiaxi Ye, Yuchen Jiang +2Physics Simulation 4D Generation
Beijing Institute of Technology
PointAction: 3D Points as Universal Action Representations for Robot Control
Jun 2, 2026Mutian Tong, Han Jiang, Qiao Feng +2Robotic Manipulation 3D Motion
University of Pennsylvania · Work done during internship at University of Pennsylvania.
Cross-Axis Feature Fusion with Joint-Wise Motion Difference Prediction for Text-Based 3D Human Motion Editing
May 31, 2026Gyojin Han, Junmo Kim3D Motion Training-Set Long-Tail Motions
School of Electrical Engineering, KAIST
Lipschitz Optimization for Formal Verification of Homographies
May 22, 2026Jean-Guillaume Durand, Panagiotis Kouvaros, Maxime Gariel +1Homography Lipschitz Continuity
Joby Aviation · Safe Intelligence
Quantitative Video World Model Evaluation for Geometric-Consistency
May 14, 2026Jiaxin Wu, Yihao Pi, Yinling Zhang +2Generative Video Models Video World Models
1Tsinghua University - IEI Lab · 2UW-Madison · 3Adobe Research
PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation
May 14, 2026Yidong Huang, Zun Wang, Han Lin +6Human Motion Generation 3D Motion
1UNC Chapel Hill · 2FieldAI · 3NTU Singapore +2
R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow
May 13, 2026Zijie Wu, Lixin Xu, Puhua Jiang +33D Motion Meshes
Huazhong University of Science and Technology, China · Tencent Hunyuan, China
GeoBlur: Epipolar Geometry Estimation from a Single Motion-Blurred Image
May 2, 2026Bao-Long Tran, Cuong Le, Fredrik Viksten +1Motion Blur Homography
Computer Vision Laboratory, Linköping University, Sweden
IAM: Identity-Aware Human Motion and Shape Joint Generation
Apr 28, 2026Wenqi Jia, Zekun Li, Abhay Mittal +6Human Motion Generation Human Motion
UIUC · Meta Reality Labs · Brown University
Multi-Camera Self-Calibration in Sports Motion Capture: Leveraging Human and Stick Poses
Apr 19, 2026Fan Yang, Changsoo Jung, Ryosuke Kawamura +1Extrinsic Calibration Camera Intrinsics
Fujitsu Research · Colorado State University
InterEdit: Navigating Text-Guided 3D Dyadic Human Motion Editing
Mar 13, 2026Yebin Yang, Di Wen, Lei Qi +103D Motion 3D Generation
Karlsruhe Institute of Technology, Germany · Hunan University, China · KAUST, Saudi Arabia +1
Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints
Mar 12, 2026Chenyangguang Zhang, Botao Ye, Boqi Chen +43D Hand Egocentric Video
1ETH Zurich · 2ETH AI Center · 3MPI for Informatics +1
MorphGS: Morphology-Adaptive Articulated 3D Motion Transfer from Videos
Jan 6, 2026Taeyeon Kim, Youngju Na, Jumin Lee +33D Motion Cross-Embodiment Retargeting
KAIST, Republic of Korea
An Optimal Algorithm for Changing from Latitudinal to Longitudinal Formation of Autonomous Aircraft Squadrons
Dec 1, 2017Paulo André Sperandio Giacomin, Elder Moreira HemerlyUnmanned Aerial Vehicles Longitudinal
Universidade Estadual de Santa Cruz Departamento de Ciências Exatas e Tecnológicas - Área de Informática Ilhéus-BA, Brasil · Instituto Tecnológico de Aeronáutica Departamento de Sistemas e Controle - Divisão de Engenharia Eletrônica São José dos Campos-SP, Brasil

Oct 1, 2026, cs.CVJ/K move · Enter open · S save

Generative Cinematographer: Composing Camera and Object Motion in 3D

Jiahan Zhang, Chaohao Yang, Namitha Guruprasad, Vivekjyoti Banerjee+3

Johns Hopkins University

3D Motion Camera Control Camera 3D Generation Motion

Open paper AskPDF arXiv

Current controllable video generation systems often rely on 2D motion trajectories or sparse drag signals for object motion. These controls are ambiguous because the same 2D trajectory can correspond to different 3D motions, especially when the camera and objects move simultaneously. We present Generative Cinematographer (GenCine), a system that lifts a single image into an editable 3D scene scaffold where artists jointly author camera and foreground motion. Artists specify a camera path and move selected foreground regions using local 3D motion handles. Several handles can move different parts of a subject independently, providing a piecewise-rigid approximation to non-rigid motion without a physics simulator or category-specific prior. To communicate these controls to a pretrained video model, we project them into guidance maps. These maps record where the controlled regions appear in each frame, assign each handle a fixed color across frames and encode the current 3D positions of its controlled points in the same world coordinate system as the background. This lets us describe object motion relative to the scene even as the camera moves. For training, we recover controls from the motion observed in real videos and use ground-truth geometry and trajectories from synthetic videos. We train a lightweight guidance branch and LoRA adapters on a pretrained Wan model to follow these controls. Our experiments show consistent camera-relative motion, improved geometric consistency under viewpoint changes, and strong controllability across diverse real-world scenes.

Momentum

Related topics

Latest papers 31