Optimal Transport-Guided Conditional Score-Based Diffusion Model

Authors: Xiang Gu, Liwei Yang, Jian Sun, Zongben Xu

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on unpaired super-resolution and semi-paired image-to-image translation demonstrated the effectiveness of the proposed OTCS model.
Researcher Affiliation Academia 1 School of Mathematics and Statistics, Xi an Jiaotong University, Xi an, China 2 Pazhou Laboratory (Huangpu), Guangzhou, China 3 Peng Cheng Laboratory, Shenzhen, China {xianggu,yangliwei}@stu.xjtu.edu.cn {jiansun,zbxu}@xjtu.edu.cn
Pseudocode Yes The pseudo-code for training uω, vω is given in Appendix A. ... The pseudo-code of the training algorithm is given in Appendix A.
Open Source Code Yes Code is available at https://github.com/XJTU-XGU/OTCS.
Open Datasets Yes We conduct extensive experiments on unpaired super-resolution and semi-paired I2I tasks... Celeb A dataset [41]. ... images of cat, fox, and leopard from AFHQ [48] dataset... translation from MNIST [49] to Chinese-MNIST [50].
Dataset Splits No The paper mentions splitting the dataset into A1, B1, C1 and training on A0, B1, and testing on C0, but it does not explicitly mention a 'validation' split or set.
Hardware Specification No The paper does not provide specific hardware details such as GPU or CPU models used for running experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., Python 3.x, PyTorch 1.x) that were used for the implementation.
Experiment Setup Yes M = 0.2 in experiments. ... where τ is set to 0.1.