Analyzing and Improving the Image Quality of StyleGAN
Tero Karras,Samuli Laine,Miika Aittala,Janne Hellsten,Jaakko Lehtinen,Timo Aila +5 more
- 14 Jun 2020
- pp 8110-8119
TL;DR: In this paper, the authors propose to redesign the generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent codes to images.
read more
Abstract: The style-based GAN architecture (StyleGAN) yields state-of-the-art results in data-driven unconditional generative image modeling. We expose and analyze several of its characteristic artifacts, and propose changes in both model architecture and training methods to address them. In particular, we redesign the generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent codes to images. In addition to improving image quality, this path length regularizer yields the additional benefit that the generator becomes significantly easier to invert. This makes it possible to reliably attribute a generated image to a particular network. We furthermore visualize how well the generator utilizes its output resolution, and identify a capacity problem, motivating us to train larger models for additional quality improvements. Overall, our improved model redefines the state of the art in unconditional image modeling, both in terms of existing distribution quality metrics as well as perceived image quality.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
SceneComposer: Any-Level Semantic Image Synthesis
Y. Zeng,Zhe Lin,Jianming Zhang,Qing Liu,John Collomosse,Jason Kuen,Vishal M. Patel +6 more
- 01 Jun 2023
TL;DR: SceneComposer generates high-quality images from semantic layouts of any precision level, ranging from text to detailed shapes. It supports flexible control over image generation based on user input and offers a wide range of capabilities for different drawing expertise and stages of the creative process.
18
Prompt-Free Diffusion: Taking “Text” Out of Text-to-Image Diffusion Models
Xingqian Xu,Jiayi Guo,Zhangyang Wang,Gao Huang,Irfan Essa,Humphrey Shi +5 more
- 16 Jun 2024
18
Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis
01 Jan 2022
TL;DR: Wang et al. as mentioned in this paper proposed a 3D-aware GAN, SURF-GAN, which is capable of discovering semantic attributes during training and controlling them in an unsupervised manner.
18
•Posted Content
MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation
TL;DR: A novel multi-level statistics transfer model is proposed, which disentangles and transfers multi- level appearance features from person images and merges them with pose features to reconstruct the source person images themselves so that the source images can be used as supervision for self-driven person image generation.
18
InfiniCity: Infinite-Scale City Synthesis
Chieh Hubert Lin,Hsin-Ying Lee,Willi Menapace,Menglei Chai,Aliaksandr Siarohin,Ming–Hsuan Yang,Sergey Tulyakov +6 more
- 01 Oct 2023
TL;DR: InfiniCity synthesizes infinite-scale 3D city environments from random noises, leveraging 2D and 3D data.
18
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
102.6K
U-Net: Convolutional Networks for Biomedical Image Segmentation
Olaf Ronneberger,Philipp Fischer,Thomas Brox +2 more
- 05 Oct 2015
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 01 Jan 2015
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
51.9K
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky,Jia Deng,Hao Su,Jonathan Krause,Sanjeev Satheesh,Sean Ma,Zhiheng Huang,Andrej Karpathy,Aditya Khosla,Michael S. Bernstein,Alexander C. Berg,Li Fei-Fei +11 more
TL;DR: The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) as mentioned in this paper is a benchmark in object category classification and detection on hundreds of object categories and millions of images, which has been run annually from 2010 to present, attracting participation from more than fifty institutions.