ICLR 2021 accepted papers on Image generation
40 of the 860 papers accepted at ICLR 2021 (4.7%) are on Image generation, compared with 3.3% at ICLR 2020. They fall into 5 topics.
See ICLR 2021 in the interactive map
Submitting to ICLR? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
GANs · 13 papers
- Large Scale Image Completion via Co-Modulated Generative Adversarial Networks (135 citations)
- Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis (108 citations)
- You Only Need Adversarial Supervision for Semantic Image Synthesis (70 citations)
- Using latent space regression to analyze and leverage compositionality in GANs (29 citations)
- Creative Sketch Generation (21 citations)
- CcGAN: Continuous Conditional Generative Adversarial Networks for Image Generation (18 citations)
- A Geometric Analysis of Deep Generative Image Models and Its Applications (15 citations)
- GAN "Steerability" without optimization (11 citations)
- Group Equivariant Generative Adversarial Networks (8 citations)
- GANs Can Play Lottery Tickets Too (5 citations)
- Adaptive Procedural Task Generation for Hard-Exploration Problems (3 citations)
- Refining Deep Generative Models via Discriminator Gradient Flow (3 citations)
and 1 more in the interactive map.
Autoregressive and latent generation · 11 papers
- DiffWave: A Versatile Diffusion Model for Audio Synthesis (119 citations)
- Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis (81 citations)
- Counterfactual Generative Networks (36 citations)
- End-to-end Adversarial Text-to-Speech (31 citations)
- MODALS: Modality-agnostic Automated Data Augmentation in the Latent Space (22 citations)
- The Intrinsic Dimension of Images and Its Impact on Learning (22 citations)
- Decentralized Attribution of Generative Models (6 citations)
- Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling (6 citations)
- Colorization Transformer (5 citations)
- Decoupling Global and Local Representations via Invertible Generative Flows (1 citation)
- Private Image Reconstruction from System Side Channels Using Generative Models
Fast diffusion sampling · 9 papers
- Score-Based Generative Modeling through Stochastic Differential Equations (1,252 citations)
- Denoising Diffusion Implicit Models (102 citations)
- WaveGrad: Estimating Gradients for Waveform Generation (44 citations)
- Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images (42 citations)
- Adversarial score matching and improved sampling for image generation (29 citations)
- Learning Energy-Based Models by Diffusion Recovery Likelihood (15 citations)
- Learning Energy-Based Generative Models via Coarse-to-Fine Expanding and Sampling (10 citations)
- Anytime Sampling for Autoregressive Models via Ordered Autoencoding (6 citations)
- Improved Autoregressive Modeling with Distribution Smoothing (3 citations)
Image restoration · 5 papers
- Learning Accurate Entropy Model with Global Reference for Image Compression (31 citations)
- Async-RED: A Provably Convergent Asynchronous Block Parallel Stochastic Method using Deep Denoising Priors (9 citations)
- GAN2GAN: Generative Noise Learning for Blind Denoising with Single Noisy Images (9 citations)
- Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders (3 citations)
- An Unsupervised Deep Learning Approach for Real-World Image Denoising
