no code implementations • 29 Sep 2021 • Jiancheng Liu, Yu Fang, Mingrui Zhang, Jiasheng Zhang, Yidong Ma, Minchen Li, Yuanming Hu, Chenfanfu Jiang, Tiantian Liu
Differentiable physics enables efficient gradient-based optimizations of neural network (NN) controllers.
no code implementations • 19 Feb 2021 • Siyuan Shen, Yang Yin, Tianjia Shao, He Wang, Chenfanfu Jiang, Lei Lan, Kun Zhou
This paper provides a new avenue for exploiting deep neural networks to improve physics-based simulation.
no code implementations • 15 Sep 2020 • Siyuan Shen, Tianjia Shao, Kun Zhou, Chenfanfu Jiang, Feng Luo, Yin Yang
We believe our method will inspire a wide-range of new algorithms for deep learning and numerical optimization.
2 code implementations • 2 Mar 2020 • Yue Li, Xuan Li, Minchen Li, Yixin Zhu, Bo Zhu, Chenfanfu Jiang
A quadrature-level connectivity graph-based method is adopted to avoid the artificial checkerboard issues commonly existing in multi-resolution topology optimization methods.
Computational Physics Computational Engineering, Finance, and Science Graphics
1 code implementation • 18 Nov 2019 • Xinlei Wang, Minchen Li, Yu Fang, Xinxin Zhang, Ming Gao, Min Tang, Danny M. Kaufman, Chenfanfu Jiang
We propose Hierarchical Optimization Time Integration (HOT) for efficient implicit time-stepping of the Material Point Method (MPM) irrespective of simulated materials and conditions.
Graphics
1 code implementation • CVPR 2018 • Siyuan Qi, Yixin Zhu, Siyuan Huang, Chenfanfu Jiang, Song-Chun Zhu
We present a human-centric method to sample and synthesize 3D room layouts and 2D images thereof, to obtain large-scale 2D/3D image data with perfect per-pixel ground truth.
no code implementations • 1 Apr 2017 • Chenfanfu Jiang, Siyuan Qi, Yixin Zhu, Siyuan Huang, Jenny Lin, Lap-Fai Yu, Demetri Terzopoulos, Song-Chun Zhu
We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the purposes of training, benchmarking, and diagnosing learning-based computer vision and robotics algorithms.
no code implementations • CVPR 2016 • Yixin Zhu, Chenfanfu Jiang, Yibiao Zhao, Demetri Terzopoulos, Song-Chun Zhu
We propose a notion of affordance that takes into account physical quantities generated when the human body interacts with real-world objects, and introduce a learning framework that incorporates the concept of human utilities, which in our opinion provides a deeper and finer-grained account not only of object affordance but also of people's interaction with objects.