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
DDE-GAN: Integrating a Data-driven Design Evaluator into Generative Adversarial Networks for Desirable and Diverse Concept Generation
TL;DR: In this article , a multimodal Data-driven Design Evaluation (DDE) model is developed to guide the generative process by automatically predicting user sentiments for the generated samples based on large-scale user reviews of previous designs.
19
Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style
Shuai Tan,Bin Ji,Ye Pan +2 more
- 11 Mar 2024
TL;DR: This paper presents Style2Talker, an audio-driven talking face generation method that integrates emotion style and art style, utilizing large-scale pretrained models and latent diffusion models to produce high-resolution, artistically stylized talking head videos with improved audio-lip synchronization and emotional expression.
•Posted Content
STEEX: Steering Counterfactual Explanations with Semantics
TL;DR: In this paper, a new generative counterfactual explanation framework is proposed to produce plausible and sparse modifications which preserve the overall scene structure, where users can guide the generation of counterfactuallys by specifying a set of semantic regions of the query image the explanation must be about.
19
•Posted Content
Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs
Hui-Po Wang,Ning Yu,Mario Fritz +2 more
TL;DR: This work shows that state-of-the-art GAN models – such as they are being publicly released by researchers and industry – can be used for a range of applications beyond unconditional image generation, by an iterative scheme that also allows gaining control over the image generation process despite the highly non-linear latent spaces of the latest GAN model.
19
One-Shot Adaptation of GAN in Just One CLIP
TL;DR: OneshotCLIP as discussed by the authors employs a two-step training strategy: reference image search in the source generator using a CLIP-guided latent optimization, followed by generator fine-tuning with a novel loss function that imposes CLIP space consistency between the source and adapted generators.
19
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.