AI Paper Atlas

Research map / Image generation / Editing and style transfer

Photographic Image Synthesis With Cascaded Refinement Networks

Qifeng Chen, Vladlen Koltun

ICCV 2017 · Image generation › Editing and style transfer · approach: Image-to-image translation · 908 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train with VGG-19 feature matching loss instead of image-space loss (ablation)CRN · CityscapesCRN preferred over baseline (%): 99.7%Improved
train with VGG-19 feature matching loss instead of image-space loss (ablation)CRN · NYUCRN preferred over baseline (%): 91.4%Improved
use cascaded refinement architecture instead of encoder-decoder (u-net) (ablation)CRN · CityscapesCRN preferred over baseline (%): 78.3%Improved
use cascaded refinement architecture instead of encoder-decoder (u-net) (ablation)CRN · NYUCRN preferred over baseline (%): 71.2%Improved
use cascaded refinement architecture instead of full-resolution dilated network (ablation)CRN · CityscapesCRN preferred over baseline (%): 67.7%Improved
use cascaded refinement architecture instead of full-resolution dilated network (ablation)CRN · NYUCRN preferred over baseline (%): 65.8%Improved
regression with perceptual loss instead of GAN plus semantic segmentation lossCRN · CityscapesCRN preferred over baseline (%): 98.5%Improved
regression with perceptual loss instead of GAN plus semantic segmentation lossCRN · NYUCRN preferred over baseline (%): 82.3%Improved
direct regression network instead of conditional GAN of Isola et al.CRN · CityscapesCRN preferred over baseline (%): 96.9%Improved
direct regression network instead of conditional GAN of Isola et al.CRN · NYUCRN preferred over baseline (%): 77.2%Improved
add diversity loss with multiple outputs (k=9) (ablation)CRN · NYU validation layoutsdiversity (qualitative)Improved
compare CRN with Pix2pix at 1/8 s exposureCRN · Cityscapes time-limitedCRN preferred over baseline (%): 73.4%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy