Cover Image

Learning to Control Physically-simulated 3D Characters via Generating and Mimicking 2D Motions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Jianan, Chen, Xiao, Huang, Tao, Wong, Tien-Tsin
Format:	Preprint
Published:	2025
Subjects:	Graphics Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Physics-based Scene Layout Generation from Human Motion
by: Li, Jianan, et al.
Published: (2024)

Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations
by: Guo, Ruoxi, et al.
Published: (2024)

Generative Motion Stylization of Cross-structure Characters within Canonical Motion Space
by: Zhang, Jiaxu, et al.
Published: (2024)

CharNeRF: 3D Character Generation from Concept Art
by: Chu, Eddy, et al.
Published: (2024)

C3Editor: Achieving Controllable Consistency in 2D Model for 3D Editing
by: Tao, Zeng, et al.
Published: (2025)

DreamCube: 3D Panorama Generation via Multi-plane Synchronization
by: Huang, Yukun, et al.
Published: (2025)

LucidDreaming: Controllable Object-Centric 3D Generation
by: Wang, Zhaoning, et al.
Published: (2023)

Unsupervised Cross-Domain Regression for Fine-grained 3D Game Character Reconstruction
by: Wen, Qi, et al.
Published: (2024)

MaskAdapt: Learning Flexible Motion Adaptation via Mask-Invariant Prior for Physics-Based Characters
by: Park, Soomin, et al.
Published: (2026)

Motion In-Betweening for Densely Interacting Characters
by: Zhang, Xiaotang, et al.
Published: (2025)

STAR: Skeleton-aware Text-based 4D Avatar Generation with In-Network Motion Retargeting
by: Chai, Zenghao, et al.
Published: (2024)

AnyAct: Towards Human Reenactment of Character Motion From Video
by: Chen, Liuhan, et al.
Published: (2026)

Make-It-Animatable: An Efficient Framework for Authoring Animation-Ready 3D Characters
by: Guo, Zhiyang, et al.
Published: (2024)

Coin3D: Controllable and Interactive 3D Assets Generation with Proxy-Guided Conditioning
by: Dong, Wenqi, et al.
Published: (2024)

Real2Edit2Real: Generating Robotic Demonstrations via a 3D Control Interface
by: Zhao, Yujie, et al.
Published: (2025)

Object-Aware 4D Human Motion Generation
by: Gui, Shurui, et al.
Published: (2025)

Sketch2Motion: Text-driven 2D Sketch to 3D Animation via Diffusion-guided Skeleton Optimization
by: Rai, Gaurav, et al.
Published: (2026)

DreamCinema: Cinematic Transfer with Free Camera and 3D Character
by: Chen, Weiliang, et al.
Published: (2024)

Physically Plausible Human-Object Rendering from Sparse Views via 3D Gaussian Splatting
by: Wang, Weiquan, et al.
Published: (2025)

DetailGen3D: Generative 3D Geometry Enhancement via Data-Dependent Flow
by: Deng, Ken, et al.
Published: (2024)

Survey on Fundamental Deep Learning 3D Reconstruction Techniques
by: Bai, Yonge, et al.
Published: (2024)

MotionFix: Text-Driven 3D Human Motion Editing
by: Athanasiou, Nikos, et al.
Published: (2024)

MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent
by: Liao, Xinyao, et al.
Published: (2025)

Synthesizing Physically Plausible Human Motions in 3D Scenes
by: Pan, Liang, et al.
Published: (2023)

Matrix-3D: Omnidirectional Explorable 3D World Generation
by: Yang, Zhongqi, et al.
Published: (2025)

SplatFont3D: Structure-Aware Text-to-3D Artistic Font Generation with Part-Level Style Control
by: Gan, Ji, et al.
Published: (2025)

DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation
by: Huang, Yukun, et al.
Published: (2023)

Interactive Character Control with Auto-Regressive Motion Diffusion Models
by: Shi, Yi, et al.
Published: (2023)

HiFi-Mesh: High-Fidelity Efficient 3D Mesh Generation via Compact Autoregressive Dependence
by: Li, Yanfeng, et al.
Published: (2026)

Material Anything: Generating Materials for Any 3D Object via Diffusion
by: Huang, Xin, et al.
Published: (2024)

CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner
by: Li, Weiyu, et al.
Published: (2024)

SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control
by: Mu, Yuxuan, et al.
Published: (2025)

Express4D: Expressive, Friendly, and Extensible 4D Facial Motion Generation Benchmark
by: Aloni, Yaron, et al.
Published: (2025)

DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusion
by: Huang, Yukun, et al.
Published: (2024)

CTRL-D: Controllable Dynamic 3D Scene Editing with Personalized 2D Diffusion
by: He, Kai, et al.
Published: (2024)

Generic 3D Diffusion Adapter Using Controlled Multi-View Editing
by: Chen, Hansheng, et al.
Published: (2024)

Recovering 3D Shapes from Ultra-Fast Motion-Blurred Images
by: Yu, Fei, et al.
Published: (2026)

See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting
by: Lu, Dongyue, et al.
Published: (2025)

RACon: Retrieval-Augmented Simulated Character Locomotion Control
by: Mu, Yuxuan, et al.
Published: (2024)

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation
by: Petrovich, Mathis, et al.
Published: (2024)