Computer Visions
🖼 Generative Adversarial Networks : Paper Review (Github)
GAN Basics
-
GAN
: Generative Adversarial Networks (NIPS 2014) : arxiv, review -
DCGAN
: Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks (ICLR 2016) : arxiv, review
Conditional GAN
-
CGAN
: Conditional Generative Adversarial Nets (2014) : arxiv, review -
ACGAN
: Conditional Image Synthesis With Auxiliary Classifier GANs (ICML 2017) : arxiv, review -
Supervised Approach
Pix2Pix
: Image-to-Image Translation with Conditional Adversarial Networks (CVPR 2017) : arxiv, reviewGAN Dissection
: Visualizing and Understanding Generative Adversarial Networks (ICLR 2019) : arxiv, [review](https://happy-jihye.github.io/gan/gan-25/#111-gan-dissection, project pageGauGAN
: Semantic Image Synthesis with Spatially Adaptive Normalization (SPADE) (CVPR 2019) : arxiv, review
-
Unsupervised Approach
CycleGAN
: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks (ICCV 2017) : arxiv, reviewFUNIT
: Few-Shot Unsupervised Image-to-Image Translation (ICCV 2019) : arxivCOCO-FUNIT
: Few-Shot Unsupervised Image Translation with a Content Conditioned Style Encoder (ECCV 2020) : arxivHiGAN
: Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis (IJCV 2020) : arxiv, review, project page
-
Multi Domain
BicycleGAN
: Toward Multimodal Image-to-Image Translation (NIPS 2017) : arxivStarGAN
: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation (CVPR 2018) : arxiv, reviewStarGAN v2
: Diversity Image Synthesis for Multiple Domains (CVPR 2020) : arxiv
MUNIT
: Multi-Modal Unsupervised Image-to-Image Translation (ECCV 2018) : arxiv, review
GAN Architecture
-
Progressive GAN
: Progressive Growing of GANs for Improved Quality, Stability, and Variation (ICLR 2018) : arxiv, review -
StyleGAN
: A Style-Based Generator Architecture for Generative Adversarial Networks (CVPR 2019) : arxiv, review-
StyleGAN v2
: Analyzing and Improving the Image Quality of StyleGAN (2020) : arxiv, review -
StyleGAN-ADA
: Training Generative Adversarial Networks with Limited Data (NeurlPS 2020) : arxiv : review #01, #02 -
StyleGAN v3
: Alias-Free Generative Adversarial Networks (NeurIPS 2021) : arxiv, code, project, review
-
-
BigGAN
: Large Scale GAN Training for High Fidelity Natural Image Synthesis (2019) : arxiv
Text-to-Image
-
Generative Adversarial Text to Image Synthesis (ICML 2016) : arxiv, review
-
TediGAN
: Text-Guided Diverse Face Image Generation and Manipulation (CVPR 2021) : arxiv, code -
StyleCLIP
: Text-Driven Manipulation of StyleGAN Imagery (arXiv 2021) : arxiv, review DALLE
: Zero-Shot Text-to-Image Generation (ICML 2021) : arxiv, project page- Paint by Word (2021) : arxiv
Improved Training Techniques
-
SS-GAN
: Self-Supervised GANs via Auxiliary Rotation Loss (CVPR 2019) : paper, review -
CR-GAN
: Consistency Regularization for Generative Adversarial Networks (ICLR 2020) : arxiv, review -
ICR-GAN
: Improved Consistency Regularization for GANs (AAAI 2021) : arxiv, review
GAN Inversion
- Latent Optimization
Image2stylegan
: How to embed images into the stylegan latent space? (ICCV 2019) : arxiv, reviewImage2stylegan++
: How to edit the embedded images? (CVPR 2020) : arxivStyleFlow
: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows (ACM TOG 2021) : arxiv, review, project pageBDInvert
: GAN Inversion for Out-of-Range Images with Geometric Transformations (ICCV 2021) : arxiv, review, code
- Encoder
- Hybrid approach
stylegan-encoder
: codeIdInvert
: In-Domain GAN Inversion for Real Image Editing (ECCV 2020) : arxiv, review, code
Disentangled Manipulation
GANSpace
: Discovering Interpretable GAN Controls (NeurIPS 2020) : arxiv, review, codeGAN-Latent-Discovery
: Unsupervised Discovery of Interpretable Directions in the GAN Latent Space (2020) : arxiv, codeEditing in style
: Uncovering the Local Semantics of GANs (CVPR 2020) : arxiv, codeHiGAN
: Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis (IJCV 2020) : arxiv, review, project pageInterFaceGAN
: Interpreting the Latent Space of GANs for Semantic Face Editing (CVPR 2020) : arxiv, review, project pageCDDFM3D
: Cross-Domain and Disentangled Face Manipulation with 3D Guidance (2021) : arxiv, review, codeGHFeat
: Generative Hierarchical Features from Synthesizing Images (CVPR 2021) : arxiv, project pageStyleSpace
: StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation (2021) : arxiv, code, code2StyleFlow
: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows (ACM TOG 2021) : arxiv, review, project pageHessian Penalty
: A weak prior for unsupervised disentanglement (ECCV 2020) : arxiv, review, project page
Image Editing
StyleCLIP
: Text-Driven Manipulation of StyleGAN Imagery (arXiv 2021) : arxiv, review, codesefa
: Closed-Form Factorization of Latent Semantics in GANs (CVPR 2021) : arxiv, review, codeEigenGAN
: Layer-Wise Eigen-Learning for GANs : arxiv, review, codeStyleMapGAN
: Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing (CVPR 2021) : arxiv, codeSEAN
: Image Synthesis with Semantic Region-Adaptive Normalization (CVPR 2020) : arxiv, codeCDDFM3D
: Cross-Domain and Disentangled Face Manipulation with 3D Guidance (2021) : arxiv, review, codeMocoGAN-HD
: A Good Image Generator Is What You Need for High-Resolution Video Synthesis (ICLR 2021) : arxiv, review, code, project
Webtoon/Anime GAN & Image Blending
Cartoon-StyleGAN
: Fine-tuning StyleGAN2 for Cartoon Face Generation (arxiv 2021) : arxiv, review, codeBlendGAN
: Implicitly GAN Blending for Arbitrary Stylized Face Generation (NeurIPS 2021) : arxiv, project, codeHifiFace
: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping (IJCAI 2021) : arxivAnimeGAN
: A Novel Lightweight GAN for Photo Animation (ISICA 2019)StyleGAN of All Trades
: Image Manipulation with Only Pretrained StyleGAN (arxiv 2021) : arxiv, code
Super Resolution
BSRGAN
: Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (ICCV 2021) : arxiv, codeReal-ESRGAN
: Training Real-World Blind Super-Resolution with Pure Synthetic Data (ICCVW 2021): arxiv, code
Sketch based Generation
GANSketching
: Sketch Your Own GAN (ICCV 2021) : arxiv, project, code, review
3D GAN & Rendering
HoloGAN
: Unsupervised learning of 3D representations from natural images (ICCV 2019): paper, codeCDDFM3D
: Cross-Domain and Disentangled Face Manipulation with 3D Guidance (2021) : arxiv, review, project, codeSofGAN
: A Portrait Image Generator with Dynamic Styling (arxiv 2021): arxiv, project, codepi-GAN
: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis (CVPR 2021): paper, project, codeStyleGANRender
: Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering (ICLR 2021) : arxiv, project pageStyleNeRF
: A Style-based 3D Aware Generator for High-resolution Image Synthesis (ICLR 2022): paperCIPS-3D
: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis (arxiv 2021): arxiv, code
😊 Talking Head : Paper list
MocoGAN-HD
: A Good Image Generator Is What You Need for High-Resolution Video Synthesis (ICLR 2021) : arxiv, review, code, project
Landmark-based Model
- Few-Shot Adversarial Learning of Realistic Neural Talking Head Models (ICCV 2019) : arxiv, review
LPD
: Neural Head Reenactment with Latent Pose Descriptors (CVPR 2020) : arxiv, project, code, reviewfs vid2vid
: Few-shot Video-to-Video Synthesis (NeurlPS 2019): arxiv, project, codeBi-layer model
: Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars (ECCV 2020): arxiv, project, code, review
Warping-based Model
X2Face
: A network for controlling face generation by using images, audio, and pose codes (ECCV 2018) : arxiv, project, reviewMonkey-Net
: Animating Arbitrary Objects via Deep Motion Transfer (CVPR 2019) : arxiv, project, code, reviewFOMM
: First Order Motion Model for Image Animation (NeurIPS 2019) : arxiv, code, reviewOSFV(face vid2vid)
: One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing (CVPR 2021): arxiv, project, reviewarticulated animation
: Motion Representations for Articulated Animation (CVPR 2021) : arxiv, code, project
📒 CS231n 강의 노트
스탠포드 대학교의 딥러닝 강의인 cs231n을 요약한 내용입니다.
1 - Introduction to Convolutional Neural Networks for Visual Recognition
2 - Image Classfication pipeline
3 - Loss Functions and Optimization
4 - Backpropagation and Neural Networks