ICLR 2017 accepted papers on Image generation
19 of the 198 papers accepted at ICLR 2017 (9.6%) are on Image generation. They fall into 6 topics.
See ICLR 2017 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 · 9 papers
- Unrolled Generative Adversarial Networks (404 citations)
- Neural Photo Editing with Introspective Adversarial Networks (245 citations)
- Mode Regularized Generative Adversarial Networks (221 citations)
- LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation (203 citations)
- Improving Generative Adversarial Networks with Denoising Feature Matching (154 citations)
- Energy-based Generative Adversarial Networks (109 citations)
- Generative Multi-Adversarial Networks (55 citations)
- On the Quantitative Analysis of Decoder-Based Generative Models (30 citations)
- Calibrating Energy-based Generative Adversarial Networks (21 citations)
Editing and style transfer · 3 papers
- A Learned Representation For Artistic Style (876 citations)
- Unsupervised Cross-Domain Image Generation (422 citations)
- What does it take to generate natural textures? (21 citations)
Autoregressive and latent generation · 3 papers
Image restoration · 2 papers
- End-to-end Optimized Image Compression (1,342 citations)
- Lossy Image Compression with Compressive Autoencoders (256 citations)
Fast diffusion sampling · 1 paper
Super-resolution · 1 paper
- Amortised MAP Inference for Image Super-resolution (322 citations)
