NeurIPS 2018 accepted papers on Image generation
37 of the 1,008 papers accepted at NeurIPS 2018 (3.7%) are on Image generation, compared with 4.2% at NeurIPS 2017. They fall into 6 topics.
See NeurIPS 2018 in the interactive map
Submitting to NeurIPS? 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
- IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis (163 citations)
- PacGAN: The power of two samples in generative adversarial networks (162 citations)
- Banach Wasserstein GAN (121 citations)
- Adversarial Regularizers in Inverse Problems (77 citations)
- Adversarial Text Generation via Feature-Mover's Distance (73 citations)
- DeepExposure: Learning to Expose Photos with Asynchronously Reinforced Adversarial Learning (71 citations)
- On GANs and GMMs (67 citations)
- Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language (65 citations)
- BinGAN: Learning Compact Binary Descriptors with a Regularized GAN (54 citations)
- Disconnected Manifold Learning for Generative Adversarial Networks (51 citations)
- Invertibility of Convolutional Generative Networks from Partial Measurements (46 citations)
- BourGAN: Generative Networks with Metric Embeddings (38 citations)
and 1 more in the interactive map.
Image restoration · 8 papers
- Joint Autoregressive and Hierarchical Priors for Learned Image Compression (345 citations)
- Non-Local Recurrent Network for Image Restoration (286 citations)
- Image Inpainting via Generative Multi-column Convolutional Neural Networks (254 citations)
- Neural Nearest Neighbors Networks (141 citations)
- Neural Proximal Gradient Descent for Compressive Imaging (115 citations)
- Training deep learning based denoisers without ground truth data (22 citations)
- Deep Generative Models for Distribution-Preserving Lossy Compression (15 citations)
- Deep, complex, invertible networks for inversion of transmission effects in multimode optical fibres (9 citations)
Autoregressive and latent generation · 8 papers
- Generalisation in humans and deep neural networks (426 citations)
- The challenge of realistic music generation: modelling raw audio at scale (116 citations)
- Unsupervised Learning of Object Landmarks through Conditional Image Generation (100 citations)
- Learning to Infer Graphics Programs from Hand-Drawn Images (94 citations)
- Towards Text Generation with Adversarially Learned Neural Outlines (37 citations)
- Nonlocal Neural Networks, Nonlocal Diffusion and Nonlocal Modeling (29 citations)
- SING: Symbol-to-Instrument Neural Generator (25 citations)
- Probabilistic Neural Programmed Networks for Scene Generation (15 citations)
Editing and style transfer · 6 papers
- FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification (298 citations)
- Unsupervised Attention-guided Image-to-Image Translation (267 citations)
- Image-to-image translation for cross-domain disentanglement (86 citations)
- Content preserving text generation with attribute controls (81 citations)
- Soft-Gated Warping-GAN for Pose-Guided Person Image Synthesis (39 citations)
- Unsupervised Learning of Artistic Styles with Archetypal Style Analysis (15 citations)
Super-resolution · 1 paper
Text-to-image diffusion · 1 paper
- Turbo Learning for CaptionBot and DrawingBot (26 citations)
