paper-with-me

Papers

Anycost GANs for Interactive Image Synthesis and Editing

2021-03-04 · CVPR 2021 1 · Ji Lin, Richard Zhang, Frieder Ganz, Song Han, Jun-Yan Zhu

Generative adversarial networks (GANs) have enabled photorealistic image synthesis and editing. However, due to the high computational cost of large-scale generators (e.g., StyleGAN2), it usually takes seconds to see the results of a single edit on edge devices, prohibiting interactive user experience. In this paper, we take inspirations from modern rendering software and propose Anycost GAN for interactive natural image editing. We train the Anycost GAN to support elastic resolutions and channels for faster image generation at versatile speeds. Running subsets of the full generator produce outputs that are perceptually similar to the full generator, making them a good proxy for preview. By using sampling-based multi-resolution training, adaptive-channel training, and a generator-conditioned discriminator, the anycost generator can be evaluated at various configurations while achieving better image quality compared to separately trained models. Furthermore, we develop new encoder training and latent code optimization techniques to encourage consistency between the different sub-generators during image projection. Anycost GAN can be executed at various cost budgets (up to 10x computation reduction) and adapt to a wide range of hardware and latency requirements. When deployed on desktop CPUs and edge devices, our model can provide perceptually similar previews at 6-12x speedup, enabling interactive image editing. The code and demo are publicly available: https://github.com/mit-han-lab/anycost-gan.

📄 PDF Abstract BibTeX arXiv:2103.03243

Code (1)

mit-han-lab/anycost-gan 공식 구현 pytorch

Tasks

Image Generation

Methods 이 논문이 사용한 방법론

Anycost GAN Anycost GAN is a type of generative adversarial network for image synthesis and editing. Given an input image, we project it into the latent space with encoder $E$ and…

Similar Papers 제목 키워드 기반

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

2017-11-30 · CVPR 2018 6 · Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu, Andrew Tao 외

We present a new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs). Conditional GANs have enabled a variety of ap…

Conditional Image GenerationFundus to Angiography GenerationImage GenerationImage-to-Image Translation+5

Improving GAN Equilibrium by Raising Spatial Awareness

2021-12-01 · CVPR 2022 1 · Jianyuan Wang, Ceyuan Yang, Yinghao Xu, Yujun Shen 외

The success of Generative Adversarial Networks (GANs) is largely built upon the adversarial training between a generator (G) and a discriminator (D). They are expected to reach a certain equilibrium where D cannot distin…

AttributeInductive Bias

SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing

2021-12-04 · CVPR 2022 1 · Yichun Shi, Xiao Yang, Yangyue Wan, Xiaohui Shen

Recent studies have shown that StyleGANs provide promising prior models for downstream tasks on image synthesis and editing. However, since the latent codes of StyleGANs are designed to control global styles, it is hard …

DisentanglementFacial EditingImage GenerationTransfer Learning

Mask-Guided Portrait Editing with Conditional GANs

2019-05-24 · CVPR 2019 6 · Shuyang Gu, Jianmin Bao, Hao Yang, Dong Chen 외

Portrait editing is a popular subject in photo manipulation. The Generative Adversarial Network (GAN) advances the generating of realistic faces and allows more face editing. In this paper, we argue about three issues in…

Data AugmentationDiversityFace GenerationFace Parsing+2

Interpreting Generative Adversarial Networks for Interactive Image Generation

2021-08-10 · Bolei Zhou

Significant progress has been made by the advances in Generative Adversarial Networks (GANs) for image generation. However, there lacks enough understanding of how a realistic image is generated by the deep representatio…

Image Generation