BriefGPT.xyz
Nov, 2023
潜在扩散逆解算的文本正则化
Regularization by Texts for Latent Diffusion Inverse Solvers
HTML
PDF
Jeongsol Kim, Geon Yeong Park, Hyungjin Chung, Jong Chul Ye
TL;DR
通过将预期解决方案的文本描述在逆采样阶段中进行正则化，我们引入了一种创新的潜变扩散逆求解器（TReg），通过感知偏见解决潜变扩散逆求解器中的歧义，从而成功缓解了这类问题的歧义，提高了效果和准确性。
Abstract
The recent advent of
diffusion models
has led to significant progress in solving
inverse problems
, leveraging these models as effective
generativ
→