paper-with-me

홈 › Papers

The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing

2024-06-15 · CVPR 2024 1 · Denis Bobkov, Vadim Titov, Aibek Alanov, Dmitry Vetrov

The task of manipulating real image attributes through StyleGAN inversion has been extensively researched. This process involves searching latent variables from a well-trained StyleGAN generator that can synthesize a real image, modifying these latent variables, and then synthesizing an image with the desired edits. A balance must be struck between the quality of the reconstruction and the ability to edit. Earlier studies utilized the low-dimensional W-space for latent search, which facilitated effective editing but struggled with reconstructing intricate details. More recent research has turned to the high-dimensional feature space F, which successfully inverses the input image but loses much of the detail during editing. In this paper, we introduce StyleFeatureEditor -- a novel method that enables editing in both w-latents and F-latents. This technique not only allows for the reconstruction of finer image details but also ensures their preservation during editing. We also present a new training pipeline specifically designed to train our model to accurately edit F-latents. Our method is compared with state-of-the-art encoding approaches, demonstrating that our model excels in terms of reconstruction quality and is capable of editing even challenging out-of-domain examples. Code is available at https://github.com/AIRI-Institute/StyleFeatureEditor.

📄 PDF Abstract BibTeX arXiv:2406.10601

Code (1)

airi-institute/stylefeatureeditor 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
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…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…
HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
Adaptive Instance Normalization 설명 없음
R1 Regularization R_INLINE_MATH_1 Regularization is a regularization technique and gradient penalty for training [generative adversarial…
StyleGAN 설명 없음

Similar Papers 제목 키워드 기반

DevilSight: Augmenting Monocular Human Avatar Reconstruction through a Virtual Perspective

2025-08-30 · Yushuo Chen, Ruizhi Shao, Youxin Pang, Hongwen Zhang 외 arxiv

We present a novel framework to reconstruct human avatars from monocular videos. Recent approaches have struggled either to capture the fine-grained dynamic details from the input or to generate plausible details at nove…

Video Generation

FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Dataset

2022-03-26 · CVPR 2022 1 · Lizhen Wang, ZhiYuan Chen, Tao Yu, Chenguang Ma 외

We present FaceVerse, a fine-grained 3D Neural Face Model, which is built from hybrid East Asian face datasets containing 60K fused RGB-D images and 2K high-fidelity 3D head scan models. A novel coarse-to-fine structure …

2k3D Face ReconstructionFace ModelFace Reconstruction

“Devils Are in the Details”: Annotating Specificity of Clinical Advice from Medical Literature

2022-07-01 · NAACL (unimplicit) 2022 7 · Yingya Li, Bei Yu

Prior studies have raised concerns over specificity issues in clinical advice. Lacking specificity — explicitly discussed detailed information — may affect the quality and implementation of clinical advice in medical pra…

Specificity

Unsupervised Facial Performance Editing via Vector-Quantized StyleGAN Representations

2023-01-01 · ICCV 2023 1 · Berkay Kicanaoglu, Pablo Garrido, Gaurav Bharaj

High-fidelity virtual human avatar applications create a need for photorealistic video face synthesis with controllable semantic editing over facial features. While recent generative neural methods have shown signifi…

Face GenerationFace ModelFace ReenactmentQuantization+1

Warping the Residuals for Image Editing with StyleGAN

2023-12-18 · Ahmet Burak Yildirim, Hamza Pehlivan, Aysegul Dundar

StyleGAN models show editing capabilities via their semantically interpretable latent organizations which require successful GAN inversion methods to edit real images. Many works have been proposed for inverting images i…