EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations

Authors: Min Zhao, Fan Bao, Chongxuan LI, Jun Zhu

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirically, we compare EGSDE to a large family of baselines on three widely-adopted unpaired I2I tasks under four metrics.
Researcher Affiliation Collaboration Min Zhao1, Fan Bao1, Chongxuan Li2,3 , Jun Zhu1 1Dept. of Comp. Sci. & Tech., BNRist Center, THU-Bosch ML Center, Tsinghua University, China 2 Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China 3 Beijing Key Laboratory of Big Data Management and Analysis Methods , Beijing, China 4 Pazhou Laboratory (Huangpu), Guangzhou, China
Pseudocode Yes Algorithm 1 EGSDE for unpaired image-to-image translation
Open Source Code Yes The code is available at https://github.com/ML-GSAI/EGSDE.
Open Datasets Yes Celeb A-HQ [20] contains high quality face images... AFHQ [8] consists of high-resolution animal face images...
Dataset Splits No The paper mentions using training and testing datasets for experiments but does not explicitly state the use of a separate validation dataset split.
Hardware Specification Yes Part of the computing resources supporting this work, totaled 500 A100 GPU hours, were provided by High-Flyer AI. (Hangzhou High-Flyer AI Fundamental Research Co., Ltd.).
Software Dependencies No The paper mentions using 'Euler-Maruyama solver' and implementing a 'resize function... by [45]', but does not provide specific software names with version numbers (e.g., PyTorch 1.9, TensorFlow 2.x).
Experiment Setup Yes For generation process, by default, the weight parameter λs, λi is set 500 and 2 respectively. The initial time M and denoising steps N is set 0.5T and 500 by default.