目录

生成模型笔记

• 生成模型笔记（一）：概率基础知识

• 生成模型笔记（二）：最大似然，贝叶斯和最大后验概率

• 生成模型笔记（三）：近似推断

• 生成模型笔记（四）：MCMC和Gibbs Sampling

• 生成模型笔记（五）：判别模型

• 生成模型笔记（六）：生成模型

• 生成模型笔记（七）：自回归模型

• 生成模型笔记（八）：Flow-Based Models

最优传输笔记

pytorch笔记

文章阅读记录

Large Language Models

Diffusion Models

• 001_SSSSS_ Denoising Diffusion Probabilistic Models

• 002_SSSS_ Denoising Diffusion Implicit Models

• 003_SSS_ Tackling the Generative Learning Trilemma with Denoising Diffusion GANs

• 005_SS_ Palette Image-to-Image Diffusion Models

• 006_SS_ Dual Diffusion Implicit Bridges For Image-to-Image Translation

• 008_SSSS_ Improved Denoising Diffusion Probabilistic Models

• 012_SSS_ Improving Diffusion Model Efficiency Through Patching

• 013_SSS_ Frido Feature Pyramid Diffusion for Complex Scene Image Synthesis

• 014_SSS_ High-Resolution Image Synthesis with Latent Diffusion Models

• 017_SSS_Semantic Image Synthesis via Diffusion Models

• 018_SS_High-Resolution Image Editing via Multi-Stage Blended Diffusion

• 021_SSSS_Diffusion Models Already Have a Semantic Latent Space

• 027_SSS_Direct Inversion Optimization-Free Text-Driven Real Image Editing with Diffusion Models

• 028_SSS_Fine-tuning Diffusion Models with Limited Data

• 031_SSS_Imagic Text-Based Real Image Editing with Diffusion Models

• 033_SS_Inversion-Based Creativity Transfer with Diffusion Models

• 035_SS_Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion Models

• 036_SS_Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models

• 037_SS_SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions

• 038_SSS_Multi-Architecture Multi-Expert Diffusion Models

• 039_SSS_ArtFusion: Controllable Arbitrary Style Transfer using Dual Conditional LDM

• 040 DifFSS: Diffusion Model for Few-Shot Semantic Segmentation

• 041 LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance

• 042 An Edit Friendly DDPM Noise Space: Inversion and Manipulations

• 043 MissDiff: Training Diffusion Models on Tabular Data with Missing Values

• 044_SSS_Counting Guidance for High Fidelity Text-to-Image Synthesis

• 048_SSS_Decoupled Diffusion Models with Explicit Transition Probability

• 049_SSS_Continuous Layout Editing of Single Images with Diffusion Models

• 050 Semi-Implicit Denoising Diffusion Models

• 051_SSS_SpaText Spatio-Textual Representation for Controllable Image Generation

GAN

• 004_SSSS_ Image-to-Image Translation with Conditional Adversarial Networks

• 019_SSSS_High-Resolution Image Synthesis and Semantic Manipulation with Conditioanl GANs

• 020_SSSS_A Style-Based Generator Architecture for Generative Adversarial Networks(StyleGAN)

Transformer

• 029_SSS_MaskGIT Masked Generative Image Transformer（CVPR2022）

• 030_SSS_MaskSketch Unpaired Structure-guided Masked Image Generation

VAE

Normalizing Flow

Neural Ordinary Differential Equations

• 007_SSSSS_ Neural Ordinary Differential Equtions

• 016_SSS_ GAN Inversion for Consistent Video Interpolation and Manipulation

• 007_补充_ Pytorch 反向传播和Neural ODE的反向传播

Other Classical Papers

• 015_SSSSS_ Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

3D Papers

• 022_SSS_Novel View Synthesis with Diffusion Models

• 023_SSS_Neural 3D Video Synthesis from Multi-view Video(CVPR2022)

• 024_SSS_Occupancy Flow: 4D Reconstruction by Learning Particle Dynamics(ICCV2019)

• 025_SSS_BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction

• 026_SS_MoFusion A Framework for Denoising-Diffusion-based Motion Synthesis

• 045_SS_FDNeRF Semantics-Driven Face Reconstruction Prompt Editing and Relighting with Diffusion Models

• 046_S_Edit-DiffNeRF Editing 3D Neural Radiance Fields using 2D Diffusion Model

• 047_SSS_Local 3D Editing via 3D Distillation of CLIP Knowledge

Implicit Neural Representation

• 052_SSSS_Image Generators with Conditionally-Independent Pixel Synthesis

• 053_SSSS_Implicit Neural Representations with Periodic Activation Functions

• 054_SSSS_Learning Implicit Fields for Generative Shape Modeling