no code implementations • 22 Sep 2023 • Hao Zhu, Fengyi Liu, Qi Zhang, Xun Cao, Zhan Ma
This connection ensures a seamless backpropagation of gradients from the network's output back to the input coordinates, thereby enhancing regularization.
no code implementations • 3 Apr 2023 • Hao Zhu, Shaowen Xie, Zhen Liu, Fengyi Liu, Qi Zhang, You Zhou, Yi Lin, Zhan Ma, Xun Cao
However, the expressive power of INR is limited by the spectral bias in the network training.