activity
20242026
collaborators

9 papers

cs.CV2026

Towards Reliable Human Evaluations in Gesture Generation: Insights from a Community-Driven State-of-the-Art Benchmark

Rajmund Nagy, Hendric Voss, Thanh Hoang-Minh +18

We review human evaluation practices in automatic, speech-driven 3D gesture generation and find a lack of standardisation and frequent use of flawed experimental setups. This leads…

cs.CV2026

From 2D Alignment to 3D Plausibility: Unifying Heterogeneous 2D Priors and Penetration-Free Diffusion for Occlusion-Robust Two-Hand Reconstruction

Gaoge Han, Yongkang Cheng, Zhe Chen +2

Two-hand reconstruction from monocular images is hampered by complex poses and severe occlusions, which often cause interaction misalignment and two-hand penetration. We address th…

cs.CV2026

Mirage2Matter: A Physically Grounded Gaussian World Model from Video

Zhengqing Gao, Ziwen Li, Xin Wang +12

The scalability of embodied intelligence is fundamentally constrained by the scarcity of real-world interaction data. While simulation platforms provide a promising alternative, ex…

cs.GR2025

Inter-Diffusion Generation Model of Speakers and Listeners for Effective Communication

Jinhe Huang, Yongkang Cheng, Yuming Hang +4

Full-body gestures play a pivotal role in natural interactions and are crucial for achieving effective communication. Nevertheless, most existing studies primarily focus on the ges…

cs.CV2025

HoloGest: Decoupled Diffusion and Motion Priors for Generating Holisticly Expressive Co-speech Gestures

Yongkang Cheng, Shaoli Huang

Animating virtual characters with holistic co-speech gestures is a challenging but critical task. Previous systems have primarily focused on the weak correlation between audio and…

cs.SD2024

Conditional GAN for Enhancing Diffusion Models in Efficient and Authentic Global Gesture Generation from Audios

Yongkang Cheng, Mingjiang Liang, Shaoli Huang +3

Audio-driven simultaneous gesture generation is vital for human-computer communication, AI games, and film production. While previous research has shown promise, there are still li…