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
•Posted Content
Frequency Domain Image Translation: More Photo-realistic, Better Identity-preserving
TL;DR: A novel frequency domain image translation (FDIT) framework, exploiting frequency information for enhancing the image generation process, and effectively preserves the identity of the source image, and produces photo-realistic images.
HyperInverter: Improving StyleGAN Inversion via Hypernetwork
01 Jun 2022
TL;DR: HyperInverter as mentioned in this paper uses a series of hypernetworks to recover the missing information during GAN inversion, which can yield high reconstruction quality thanks to the hypernetwork branch and excellent editability due to the inversion.
Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors
Chaofeng Chen,Xinyu Shi,Yipeng Qin,Xiaoming Li,Xiaoguang Han,Taojiannan Yang,Shihui Guo +6 more
- 26 Feb 2022
TL;DR: This work proposes Feature Matching SR (FeMaSR), which restores realistic HR images in a much more compact feature space by matching distorted LR image features to their distortion-free HR counterparts in the authors' pretrained HR priors, and decoding the matched features to obtain realisticHR images.
•Posted Content
Portrait Neural Radiance Fields from a Single Image
TL;DR: This work proposes to pretrain the weights of a multilayer perceptron (MLP), which implicitly models the volumetric density and colors, with a meta-learning framework using a light stage portrait dataset to improve the generalization to unseen faces.
84
•Posted Content
Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data
TL;DR: Wang et al. as discussed by the authors proposed a proactive and sustainable solution on deepfake detection, that is agnostic to the evolution of generative models, by introducing artificial fingerprints into the models.
83
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.