The Unreasonable Effectiveness of Deep Features as a Perceptual Metric

CVPR 2018 • Richard Zhang • Phillip Isola • Alexei A. Efros • Eli Shechtman • Oliver Wang

While it is nearly effortless for humans to quickly assess the perceptual similarity between two images, the underlying processes are thought to be quite complex. Despite this, the most widely used perceptual metrics today, such as PSNR and SSIM, are simple, shallow functions, and fail to account for many nuances of human perception... (read more)

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract

Code

Add Remove Mark official

richzhang/PerceptualSimilarity official

1,502

Puzer/stylegan-encoder

870

pbaylies/stylegan-encoder

564

ak9250/stylegan-art

328

woctezuma/stylegan2-projecting-images

↳ Quickstart in

Colab

See all 22 implementations

Tasks

Add Remove

SSIM

Datasets

Introduced in the Paper:

Perceptual Similarity

Mentioned in the Paper:

DIV2K

Results from the Paper

Edit

Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

METHOD	TYPE
Dropout	Regularization
Dense Connections	Feedforward Networks
ReLU	Activation Functions
Max Pooling	Pooling Operations
Softmax	Output Functions
Convolution	Convolutions
VGG	Convolutional Neural Networks

METHOD

TYPE

Dropout