paper-with-me

Papers

Improving generative adversarial network inversion via fine-tuning GAN encoders

2021-08-23 · Cheng Yu, Wenmin Wang, Roberto Bugiolacchi

Generative adversarial networks (GANs) can synthesize high-quality (HQ) images, and GAN inversion is a technique that discovers how to invert given images back to latent space. While existing methods perform on StyleGAN inversion, they have limited performance and are not generalized to different GANs. To address these issues, we proposed a self-supervised method to pre-train and fine-tune GAN encoders. First, we designed an adaptive block to fit different encoder architectures for inverting diverse GANs. Then we pre-train GAN encoders using synthesized images and emphasize local regions through cropping images. Finally, we fine-tune the pre-trained GAN encoder for inverting real images. Compared with state-of-the-art methods, our method achieved better results that reconstructed high-quality images on mainstream GANs. Our code and pre-trained models are available at: https://github.com/disanda/Deep-GAN-Encoders.

📄 PDF Abstract BibTeX arXiv:2108.10201

Code (4)

disanda/deep-gan-encoders 공식 구현 pytorch
disanda/dse 공식 구현 pytorch
disanda/mtv-tsa 공식 구현 pytorch
MindSpore-scientific-2/code-11/tree/main/TSA_mindspore mindspore

Tasks

Generative Adversarial NetworkImage Reconstruction

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Non-Local Operation A Non-Local Operation is a component for capturing long-range dependencies with deep neural networks. It is a generalization of the classical non-local mean operation in…
Spectral Normalization Spectral Normalization is a normalization technique used for generative adversarial networks, used to stabilize training of the discriminator. Spectral normalization has the…
Adaptive Instance Normalization 설명 없음
Adam 설명 없음

Similar Papers 제목 키워드 기반

Performance of Machine Learning Methods for Gravity Inversion: Successes and Challenges

2025-09-28 · Vahid Negahdari, Shirin Samadi Bahrami, Seyed Reza Moghadasi, Mohammad Reza Razvan arxiv

Gravity inversion is the problem of estimating subsurface density distributions from observed gravitational field data. We consider the two-dimensional (2D) case, in which recovering density models from one-dimensional (…

Dual Encoder GAN Inversion for High-Fidelity 3D Head Reconstruction from Single Images

2024-09-30 · Bahri Batuhan Bilecen, Ahmet Berke Gokmen, Aysegul Dundar

3D GAN inversion aims to project a single image into the latent space of a 3D Generative Adversarial Network (GAN), thereby achieving 3D geometry reconstruction. While there exist encoders that achieve good results in 3D…

3D geometryGenerative Adversarial Network

ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement

2021-04-06 · ICCV 2021 10 · Yuval Alaluf, Or Patashnik, Daniel Cohen-Or

Recently, the power of unconditional image synthesis has significantly advanced through the use of Generative Adversarial Networks (GANs). The task of inverting an image into its corresponding latent code of the trained …

Image GenerationReal-to-Cartoon translation

Image Inversion: A Survey from GANs to Diffusion and Beyond

2025-02-17 · Yinan Chen, Jiangning Zhang, Yali Bi, Xiaobin Hu 외

Image inversion is a fundamental task in generative models, aiming to map images back to their latent representations to enable downstream applications such as editing, restoration, and style transfer. This paper provide…

Generative Adversarial NetworkStyle TransferSurvey

Robustness in Both Domains: CLIP Needs a Robust Text Encoder

2025-06-03 · Elias Abad Rocamora, Christian Schlarmann, Naman Deep Singh, Yongtao Wu 외

Adversarial input attacks can cause a significant shift of CLIP embeddings. This can affect the downstream robustness of models incorporating CLIP in the pipeline, such as text-to-image generative models or large vision …