1 code implementation • NeurIPS 2023 • Yesom Park, Taekyung Lee, Jooyoung Hahn, Myungjoo Kang
For efficient training, we develop a variable splitting structure by introducing a gradient of the SDF as an auxiliary variable and impose the $p$-Poisson equation directly on the auxiliary variable as a hard constraint.
1 code implementation • 20 Feb 2023 • Jaemoo Choi, Yesom Park, Myungjoo Kang
Also, we propose a multi-scale training, which improves the performance compared to the diffusion process, by taking advantage of the flexibility of the forward process.
no code implementations • 2 Feb 2023 • Yesom Park, Jaemoo Choi, Changyeon Yoon, Chang hoon Song, Myungjoo Kang
Learning underlying dynamics from data is important and challenging in many real-world scenarios.