BriefGPT.xyz
Aug, 2023
DiffGANPaint：使用去噪扩散GAN进行快速修复
DiffGANPaint: Fast Inpainting Using Denoising Diffusion GANs
HTML
PDF
Moein Heidari, Alireza Morsali, Tohid Abedini, Samin Heydarian
TL;DR
本文提出了一种基于DDPM的模型，能够通过使用生成对抗网络（GAN）的生成器来建模反向扩散过程，从而以较低的采样成本填充丢失的像素，实验结果表明我们的方法在通用图像修复数据集上表现出卓越性能。
Abstract
free-form image inpainting
is the task of reconstructing parts of an image specified by an arbitrary
binary mask
. In this task, it is typically desired to generalize model capabilities to unseen mask types, rathe
→