no code implementations • 21 Nov 2017 • Aaron Walsman, Weilin Wan, Tanner Schmidt, Dieter Fox
The last several years have seen significant progress in using depth cameras for tracking articulated objects such as human bodies, hands, and robotic manipulators.
no code implementations • 5 Aug 2019 • Weilin Wan, Aaron Walsman, Dieter Fox
While recent work has shown direct estimation techniques can be quite powerful, geometric tracking methods using point clouds can provide a very high level of 3D accuracy which is necessary for many robotic applications.
no code implementations • 13 Apr 2020 • Zhaoqi Su, Weilin Wan, Tao Yu, Lingjie Liu, Lu Fang, Wenping Wang, Yebin Liu
We introduce MulayCap, a novel human performance capture method using a monocular video camera without the need for pre-scanning.
no code implementations • 25 Jun 2022 • Weilin Wan, Lei Yang, Lingjie Liu, Zhuoying Zhang, Ruixing Jia, Yi-King Choi, Jia Pan, Christian Theobalt, Taku Komura, Wenping Wang
We also observe that an object's intrinsic physical properties are useful for the object motion prediction, and thus design a set of object dynamic descriptors to encode such intrinsic properties.
no code implementations • ICCV 2023 • Zhiyang Dou, Qingxuan Wu, Cheng Lin, Zeyu Cao, Qiangqiang Wu, Weilin Wan, Taku Komura, Wenping Wang
We further demonstrate the generalizability of our method on hand mesh recovery.
no code implementations • 28 Nov 2023 • Weilin Wan, Zhiyang Dou, Taku Komura, Wenping Wang, Dinesh Jayaraman, Lingjie Liu
Controllable human motion synthesis is essential for applications in AR/VR, gaming, movies, and embodied AI.
no code implementations • 7 Dec 2023 • Weilin Wan, Yiming Huang, Shutong Wu, Taku Komura, Wenping Wang, Dinesh Jayaraman, Lingjie Liu
In this study, we introduce a learning-based method for generating high-quality human motion sequences from text descriptions (e. g., ``A person walks forward").
no code implementations • 28 Feb 2024 • Weilin Wan, Weizhong Zhang, Cheng Jin
Our neural activation prior is based on a key observation that, for a channel before the global pooling layer of a fully trained neural network, the probability of a few neurons being activated with a large response by an in-distribution (ID) sample is significantly higher than that by an OOD sample.
no code implementations • 20 Mar 2024 • Yiming Huang, Weilin Wan, Yue Yang, Chris Callison-Burch, Mark Yatskar, Lingjie Liu
Text-to-motion models excel at efficient human motion generation, but existing approaches lack fine-grained controllability over the generation process.