AI Paper Atlas

Research map / Image generation / Editing and style transfer

Photorealistic Style Transfer via Wavelet Transforms

Jaejun Yoo, Youngjung Uh, Sanghyuk Chun, Byeongkyu Kang, Jung-Woo Ha

ICCV 2019 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 417 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
replace max-pooling with Haar wavelet pooling and unpooling (no post-processing)WCT2 vs PhotoWCT · photorealistic stylizationuser preference (most preferred): 62.21%Improved
use single-pass progressive stylization instead of multi-level pipeline with removal of post-processingWCT2 · 1024x1024 runtime vs DPSTruntime (s): 3887.8 -> 4.7Improved
use wavelet pooling instead of multi-level max-pool PhotoWCT: memoryWCT2 · GPU memoryGPU memory: 51% of PhotoWCT GPU memoryImproved
add wavelet pooling instead of split pooling (ablation)WCT2 · photorealistic stylization (qualitative)fine detail preservationImproved
add wavelet pooling instead of learnable strided conv pooling (ablation)WCT2 · photorealistic stylization (qualitative)content preservation and style transferImproved
use concatenation instead of summation in wavelet unpooling (ablation)WCT2 · photorealistic stylization (qualitative)spatial detail and parameters: 1.80x parameters of sum-versionMixed
add multi-level stylization on top of WCT2 (ablation)WCT2 · statistics SSIM vs style lossstyle strength vs SSIMMixed
add progressive WCT at decoder layers conv3_2, conv2_2, conv1_2 (ablation)WCT2 · stylization strengthstylization strengthMixed
stylize only LL component instead of all wavelet components (ablation)WCT2 · stylization of edgesedge stylizationMixed
add post-processing smoothing to PhotoWCTPhotoWCT · SSIM vs style lossvisual qualityImproved

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