Unconditional Image Generation
30 papers with code • 4 benchmarks • 3 datasets
Benchmarks
These leaderboards are used to track progress in Unconditional Image Generation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
CelebA-HQ
ArtBench-10 (32x32)
Large Labelled Logo Dataset (L3D)
Most implemented papers
Learning Semantic-aware Normalization for Generative Adversarial Networks
researchmm/SariGAN
•
•
NeurIPS 2020
Such a model disentangles latent factors according to the semantic of feature channels by channel-/group- wise fusion of latent codes and feature channels.
Adaptive Weighted Discriminator for Training Generative Adversarial Networks
vasily789/adaptive-weighted-gans
•
•
CVPR 2021
Generative adversarial network (GAN) has become one of the most important neural network models for classical unsupervised machine learning.
Dual Contrastive Loss and Attention for GANs
ningyu1991/AttentionDualContrastGAN
•
•
ICCV 2021
Lastly, we study different attention architectures in the discriminator, and propose a reference attention mechanism.
ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models
jychoi118/ilvr_adm
•
•
ICCV 2021
In this work, we propose Iterative Latent Variable Refinement (ILVR), a method to guide the generative process in DDPM to generate high-quality images based on a given reference image.
Instance-Conditioned GAN
facebookresearch/ic_gan
•
•
NeurIPS 2021
Generative Adversarial Networks (GANs) can generate near photo realistic images in narrow domains such as human faces.
EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs
marsggbo/EAGAN
•
•
Some recent works try to search both generator (G) and discriminator (D), but they suffer from the instability of GAN training.
Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values
AhmedImtiazPrio/magnet-polarity
•
•
CVPR 2022
We present Polarity Sampling, a theoretically justified plug-and-play method for controlling the generation quality and diversity of pre-trained deep generative networks DGNs).
PAGER: Progressive Attribute-Guided Extendable Robust Image Generation
PAGER consists of three modules: core generator, resolution enhancer, and quality booster.
The ArtBench Dataset: Benchmarking Generative Models with Artworks
We introduce ArtBench-10, the first class-balanced, high-quality, cleanly annotated, and standardized dataset for benchmarking artwork generation.
Generator Knows What Discriminator Should Learn in Unconditional GANs
naver-ai/ggdr
•
•
Here we explore the efficacy of dense supervision in unconditional generation and find generator feature maps can be an alternative of cost-expensive semantic label maps.
