Li Haipeng

icon indicating a website link https://lhaippp.github.io/ icon indicating an email [email protected]

icon company UESTC | Megvii icon location Chengdu, China icon location PhD candidate | parle un peu français.

Results 4 issues of Li Haipeng

use CLIP to convert text into conditions

4 comment

Hi Phil, Are you considering adding CLIP into [classifier-free](https://github.com/lucidrains/denoising-diffusion-pytorch/blob/main/denoising_diffusion_pytorch/classifier_free_guidance.py) and thus implementing text2img? If so, I'm willing to do a PR.

Segmentation of Early Esophageal Cancer

Hi Jun, Thank you for the great work. I trust this repository is indeed valuable for the community! Upon viewing the teaser image, I noticed that there is limited work...

More related work and datasets

1 comment

Hi chicleee, Thanks for the great job in advance. To the best of my knowledge, I believe the repository lacks certain deep-homography and optical flow based methods and datasets. Including,...

scale up UNet with different resolution

Hi Phil, First and foremost, I would like to express my gratitude for your DDPM implementation. Our recent publications ([DMHomo](https://github.com/lhaippp/DMHomo), [RecDiffusion](https://github.com/lhaippp/RecDiffusion)) have been based on your repository, and we are...