5 papers
TurboTalk: Progressive Distillation for One-Step Audio-Driven Talking Avatar Generation
Xiangyu Liu, Feng Gao, Xiaomei Zhang +4
Existing audio-driven video digital human generation models rely on multi-step denoising, resulting in substantial computational overhead that severely limits their deployment in r…
Improving Large Vision-Language Models' Understanding for Flow Field Data
Xiaomei Zhang, Hanyu Zheng, Xiangyu Zhu +4
Large Vision-Language Models (LVLMs) have shown impressive capabilities across a range of tasks that integrate visual and textual understanding, such as image captioning and visual…
Pose-RFT: Enhancing MLLMs for 3D Pose Generation via Hybrid Action Reinforcement Fine-Tuning
Bao Li, Xiaomei Zhang, Miao Xu +3
Generating 3D human poses from multimodal inputs such as images or text requires models to capture both rich spatial and semantic correspondences. While pose-specific multimodal la…
SyncTalk++: High-Fidelity and Efficient Synchronized Talking Heads Synthesis Using Gaussian Splatting
Ziqiao Peng, Wentao Hu, Junyuan Ma +7
Achieving high synchronization in the synthesis of realistic, speech-driven talking head videos presents a significant challenge. A lifelike talking head requires synchronized coor…
MVBoost: Boost 3D Reconstruction with Multi-View Refinement
Xiangyu Liu, Xiaomei Zhang, Zhiyuan Ma +2
Recent advancements in 3D object reconstruction have been remarkable, yet most current 3D models rely heavily on existing 3D datasets. The scarcity of diverse 3D datasets results i…