zihao-zheng
Follow
Starred repositories
Shuaikai Shi, Ruiyuan Kang, Panos Liatsis "A Conditional Diffusion Model for Electrical Impedance Tomography Image Reconstruction", arXiv:2412.16979
ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models (ICCV 2021 Oral)
A MATLAB code package to perform Weighted Sparse Bayesian Learning for EIT using Bound-Optimization. Allows parametrization, compares quantitatively and qualitatively with Regularization (L2 and L1…
[ICLR 2023] Interplay between the Attention and Electrical Impedance Tomography
Image restoration with neural networks but without learning.
Implementation of Classifier Free Guidance in Pytorch, with emphasis on text conditioning, and flexibility to include multiple text embedding models
High-Resolution Image Synthesis with Latent Diffusion Models
A latent text-to-image diffusion model
组合数学引论(第2版) 课后习题解答 + 相关编程题推荐
PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)
High-Resolution Image Synthesis with Latent Diffusion Models
ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR.
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Sharpness-aware Low Dose CT Denoising Using Conditional Generative Adversarial Network
DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising
Tackling the Generative Learning Trilemma with Denoising Diffusion GANs https://arxiv.org/abs/2112.07804
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (TIP, 2017)
[CVPR 2021] Multi-Stage Progressive Image Restoration. SOTA results for Image deblurring, deraining, and denoising.
Image Denoising with Generative Adversarial Network
《美国反对美国》是王沪宁先生在上世纪80年代末赴美观察写作的。我们知道在那个年代中国对西方特别是美国的追捧有多高，所以突然看到一个学者在80年代就有如此清楚的认识，十分钦佩。由于网上只有效果很差的PDF扫描版，所以我想利用OCR技术和肉眼（人体OCR）来转成现代化的文本格式。目前已经全部完成。