Search Results for author: Sangyun Lee

Found 6 papers, 5 papers with code

Minimizing Trajectory Curvature of ODE-based Generative Models

1 code implementation27 Jan 2023 Sangyun Lee, Beomsu Kim, Jong Chul Ye

Based on the relationship between the forward process and the curvature, here we present an efficient method of training the forward process to minimize the curvature of generative trajectories without any ODE/SDE simulation.

Progressive Deblurring of Diffusion Models for Coarse-to-Fine Image Synthesis

1 code implementation16 Jul 2022 Sangyun Lee, Hyungjin Chung, Jaehyeon Kim, Jong Chul Ye

We further propose a blur diffusion as a special case, where each frequency component of an image is diffused at different speeds.

Deblurring Image Generation +1

Learning Multiple Probabilistic Degradation Generators for Unsupervised Real World Image Super Resolution

1 code implementation26 Jan 2022 Sangyun Lee, Sewoong Ahn, Kwangjin Yoon

Although the goal of training the degradation generator is to approximate the distribution of LR images given a HR image, previous works have heavily relied on the unrealistic assumption that the conditional distribution is a delta function and learned the deterministic mapping from the HR image to a LR image.

Image Super-Resolution SSIM

Inertial effects on the Brownian gyrator

no code implementations23 Dec 2020 Youngkyoung Bae, Sangyun Lee, Juin Kim, Hawoong Jeong

Another unique feature of the Langevin description is that rotation is maximized at a particular anisotropy while the stability of the rotation is minimized at a particular anisotropy or mass.

Statistical Mechanics

Learning entropy production via neural networks

2 code implementations9 Mar 2020 Dong-Kyum Kim, Youngkyoung Bae, Sangyun Lee, Hawoong Jeong

This Letter presents a neural estimator for entropy production, or NEEP, that estimates entropy production (EP) from trajectories of relevant variables without detailed information on the system dynamics.

Cannot find the paper you are looking for? You can Submit a new open access paper.