Bayesian Image Reconstruction using Deep Generative Models

Machine learning models are commonly trained end-to-end and in a supervised setting, using paired (input, output) data. Classical examples include recent super-resolution methods that train on pairs of (low-resolution, high-resolution) images... (read more)

PDF Abstract

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Denoising FFHQ BRGM LPIPS 0.24 # 1
Image Inpainting FFHQ 1024 x 1024 BRGM LPIPS 0.19 # 1
RMSE 24.28 # 1
PSNR 21.33 # 1
SSIM 0.84 # 1
Image Inpainting FFHQ 1024 x 1024 SN-PatchGAN LPIPS 0.24 # 2
RMSE 30.75 # 2
PSNR 19.67 # 2
SSIM 0.82 # 2
Image Super-Resolution FFHQ 256 x 256 - 4x upscaling BRGM PSNR 24.16 # 3
SSIM 0.70 # 6
Image Denoising FFHQ 64x64 - 4x upscaling BRGM LPIPS 0.24 # 1

Methods used in the Paper


METHOD TYPE
Path Length Regularization
Regularization
Weight Demodulation
Normalization
Convolution
Convolutions
R1 Regularization
Regularization
Leaky ReLU
Activation Functions
StyleGAN2
Generative Models