MOVE Brilliance
"Move Brilliance" research encompasses a broad range of studies focused on modeling and predicting movement, encompassing diverse applications from robotic navigation and human motion generation to chess strategy and image editing. Current research employs various techniques, including diffusion models, Gaussian processes, model predictive control, and neural networks, often incorporating scene understanding and language-based feedback to improve robustness and adaptability. This interdisciplinary field holds significant potential for advancing AI, robotics, and human-computer interaction, offering improvements in areas such as autonomous vehicle navigation, personalized healthcare, and creative content generation.
Papers
Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance
Zan Wang, Yixin Chen, Baoxiong Jia, Puhao Li, Jinlu Zhang, Jingze Zhang, Tengyu Liu, Yixin Zhu, Wei Liang, Siyuan Huang
Boosting Diffusion Models with Moving Average Sampling in Frequency Domain
Yurui Qian, Qi Cai, Yingwei Pan, Yehao Li, Ting Yao, Qibin Sun, Tao Mei