activity
20242026
collaborators

6 papers

cs.CV2026

AnyLift: Scaling Motion Reconstruction from Internet Videos via 2D Diffusion

Hongjie Li, Heng Yu, Jiaman Li +4

Reconstructing 3D human motion and human-object interactions (HOI) from Internet videos is a fundamental step toward building large-scale datasets of human behavior. Existing metho…

cs.CV2025

UniAct: Unified Motion Generation and Action Streaming for Humanoid Robots

Nan Jiang, Zimo He, Wanhe Yu +8

A long-standing objective in humanoid robotics is the realization of versatile agents capable of following diverse multimodal instructions with human-level flexibility. Despite adv…

cs.CV2025

Dynamic Motion Blending for Versatile Motion Editing

Nan Jiang, Hongjie Li, Ziye Yuan +5

Text-guided motion editing enables high-level semantic control and iterative modifications beyond traditional keyframe animation. Existing methods rely on limited pre-collected tra…

cs.CV2025

ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation

Hongjie Li, Hong-Xing Yu, Jiaman Li +1

Human-scene interaction (HSI) generation is crucial for applications in embodied AI, virtual reality, and robotics. Yet, existing methods cannot synthesize interactions in unseen e…

cs.CV2024

Autonomous Character-Scene Interaction Synthesis from Text Instruction

Nan Jiang, Zimo He, Zi Wang +4

Synthesizing human motions in 3D environments, particularly those with complex activities such as locomotion, hand-reaching, and human-object interaction, presents substantial dema…

cs.CV2024

Scaling Up Dynamic Human-Scene Interaction Modeling

Nan Jiang, Zhiyuan Zhang, Hongjie Li +6

Confronting the challenges of data scarcity and advanced motion synthesis in human-scene interaction modeling, we introduce the TRUMANS dataset alongside a novel HSI motion synthes…