This repository aims to collect cool generative models published in main AI conferences (e.g., CVPR, ICCV and ECCV) since 30 May 2021.
NOTE: If your paper is not in the list, plese feel free to raise an issue or drop me an e-mail.
BTW, blog1 and blog2 are great places to learn all kinds of generative models.
Some excellent blogs in 3D blog, blog.
Deep learning resource: foundations of deep learning, google colab.
| Title | link | Venue |
|---|---|---|
| CoordGAN: Self-Supervised Dense Correspondences Emerge from GANs | [link] | CVPR |
| Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer | [link] | CVPR |
| InsetGAN for Full-Body Image Generation | [link] | CVPR |
| Splicing ViT Features for Semantic Appearance Transfer | [link] | CVPR |
| Hierarchical Text-Conditional Image Generation with CLIP Latents | [link] | - |
| StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation | [link] | - |
| StyleSwin: Transformer-based GAN for High-resolution Image Generation | [link] | - |
| LATENT IMAGE ANIMATOR: LEARNING TO ANIMATE IMAGE VIA LATENT SPACE NAVIGATION | [link] | ICLR |
| Title | link | Venue |
|---|---|---|
| GRAM: Generative Radiance Manifolds for 3D-Aware Image Generation | [link] | - |
| Improving GAN Equilibrium by Raising Spatial Awareness | [link] | - |
| Vector Quantized Diffusion Model for Text-to-Image Synthesis | [link] | - |
| AnimeCeleb: Large-Scale Animation CelebFaces Dataset via Controllable 3D Synthetic Models | [link] | - |
| Diffusion Models Beat GANs on Image Synthesis | [link] | NeurIPS |
| Towards Scalable Unpaired Virtual Try-On via Patch-Routed Spatially-Adaptive GAN | [link] | NeurIPS |
| Instance-Conditioned GAN | [link] | NeurIPS |
| On the Frequency Bias of Generative Models | [link] | NeurIPS |
| Projected GANs Converge Faster | [link] | NeurIPS |
| BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation | [link] | NeurIPS |
| Score-based Generative Modeling in Latent Space | [link] | NeurIPS |
| NCP-VAE: VARIATIONAL AUTOENCODERS WITH NOISE CONTRASTIVE PRIORS | [link] | NeurIPS |
| D2C: Diffusion-Decoding Models for Few-Shot Conditional Generation | [link] | NeurIPS |
| Modeling Clothing as a Separate Layer for an Animatable Human Avatar | [link] | SIGGRAPH Asia |
| FreeStyleGAN: Free-view Editable Portrait Rendering with the Camera Manifold | [link] | SIGGRAPH Asia |
| Detail Me More: Improving GAN’s photo-realism of complex scenes | [link] | ICCV |
| Learning Realistic Human Reposing using Cyclic Self-Supervision with 3D Shape, Pose, and Appearance Consistency | [link] | ICCV |
| Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit Editing | [link] | ICCV |
| Latent Transformations via NeuralODEs for GAN-Based Image Editing | [link] | ICCV |
| WarpedGANSpace: Finding non-linear RBF paths in GAN latent space | [link] | ICCV |
| The Animation Transformer: Visual Correspondence via Segment Matching | [link] | ICCV |
| Disentangled Lifespan Face Synthesis | [link] | ICCV |
| StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery | [link] | ICCV |
| From Continuity to Editability: Inverting GANs with Consecutive Images | [link] | ICCV |
| EigenGAN: Layer-Wise Eigen-Learning for GANs | [link] | ICCV |
| Labels4Free: Unsupervised Segmentation using StyleGAN | [link] | ICCV |
| 3DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variations | [link] | ICCV |
| Frequency Domain Image Translation: More Photo-realistic, Better Identity-preserving | [link] | ICCV |
| ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models | [link] | ICCV |
| Sketch Your Own GAN | [link] | ICCV |
| Image Synthesis and Editing with Stochastic Differential Equations | [link] | - |
| StyleVideoGAN: A Temporal Generative Model using a Pretrained StyleGAN | [link] | - |
| Understanding Noise Injection in GANs | [link] | ICML |
| Sliced Iterative Normalizing Flows | [link] | ICML |
| Improved Denoising Diffusion Probabilistic Models | [link] | ICML |
| Generative Adversarial Transformers | [link] | ICML |
| Simple and Effective VAE Training with Calibrated Decoders | [link] | ICML |
| CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders | [link] | - |
| Zero-Shot non-adversarial domain adaptation of pre-trained generators | [link] | - |
| Alias-Free Generative Adversarial Networks | [link] | - |
| InfinityGAN: Towards Infinite-Resolution Image Synthesis | [link] | - |
| GANs N’ Roses: Stable, Controllable, Diverse Image to Image Translation (works for videos too!) | [link] | - |
| Paint by Word | [link] | - |
| Coarse-to-Fine: Facial Structure Editing of Portrait Images via Latent Space Classifications | [link] | SIGGRAPH |
| AgileGAN: Stylizing Portraits by Inversion-Consistent Transfer Learning | [link] | SIGGRAPH |
| StyleCariGAN:Caricature Generation via StyleGAN Feature Map Modulation | [link] | SIGGRAPH |
| Only a Matter of Style: Age Transformation Using a Style-Based Regression Model | [link] | SIGGRAPH |
| Designing an Encoder for StyleGAN Image Manipulation | [link] | SIGGRAPH |
| One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing | [link] | CVPR |
| Few-shot Image Generation via Cross-domain Correspondence | [link] | CVPR |
| HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms | [link] | CVPR |
| Image Generators with Conditionally-Independent Pixel Synthesis | [link] | CVPR |
| Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation | [link] | CVPR |
| Anycost GANs for Interactive Image Synthesis and Editing | [link] | CVPR |
| Closed-Form Factorization of Latent Semantics in GANs | [link] | CVPR |
| DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort | [link] | CVPR |
| Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing | [link] | CVPR |
| TediGAN: Text-Guided Diverse Face Image Generation and Manipulation | [link] | CVPR |
| LOHO: Latent Optimization of Hairstyles via Orthogonalization | [link] | CVPR |
| Navigating the GAN Parameter Space for Semantic Image Editing | [link] | CVPR |
| PISE: Person Image Synthesis and Editing with Decoupled GAN | [link] | CVPR |
| Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinement | [link] | CVPR |
| MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation | [link] | CVPR |
| SCORE-BASED GENERATIVE MODELING THROUGH STOCHASTIC DIFFERENTIAL EQUATIONS | [link] | ICLR |