Data to 7 Oct 2026

Photorealistic Style Transfer via Wavelet Transforms

arXiv 1903.09760 ↗First posted 23 Mar 2019cs.CVcited by 166

Not on the map. Why?

Abstract (arXiv)

Recent style transfer models have provided promising artistic results. However, given a photograph as a reference style, existing methods are limited by spatial distortions or unrealistic artifacts, which should not happen in real photographs. We introduce a theoretically sound correction to the network architecture that remarkably enhances photorealism and faithfully transfers the style. The key ingredient of our method is wavelet transforms that naturally fits in deep networks. We propose a wavelet corrected transfer based on whitening and coloring transforms (WCT2) that allows features to preserve their structural information and statistical properties of VGG feature space during stylization. This is the first and the only end-to-end model that can stylize a 1024×1024 resolution image in 4.7 seconds, giving a pleasing and photorealistic quality without any post-processing. Last but not least, our model provides a stable video stylization without temporal constraints. Our code, generated images, and pre-trained models are all available at https://github.com/ClovaAI/WCT2.

Key facts. Cited by 166 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 44; 2022: 40; 2023: 34; 2024: 19; 2025: 16; 2026: 13.

166 papers.

Sort:

By area:

2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 634
2022Splicing ViT Features for Semantic Appearance Transfercited by 209
2021CLIPstyler: Image Style Transfer with a Single Text Conditioncited by 203
2021StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generatorscited by 164
2021EditGAN: High-Precision Semantic Image Editingcited by 156
2022Diffusion-based Image Translation using Disentangled Style and Content Representationcited by 148
2022StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learningcited by 140
2023Cross-Image Attention for Zero-Shot Appearance Transfercited by 135
2022Wavelet Diffusion Models are fast and scalable Image Generatorscited by 116
2021ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flowscited by 113
2021Enhancing Photorealism Enhancementcited by 74
2022Back to the Source: Diffusion-Driven Test-Time Adaptationcited by 71

38 more

2021The Spatially-Correlative Loss for Various Image Translation Taskscited by 66
2021High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Networkcited by 61
2021SSH: A Self-Supervised Framework for Image Harmonizationcited by 60
2023Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfercited by 59
2022UPST-NeRF: Universal Photorealistic Style Transfer of Neural Radiance Fields for 3D Scenecited by 47
2021Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Expertscited by 46
2022CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfercited by 46
2021Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentationcited by 44
2022Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Taskscited by 42
2021Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfercited by 41
2021Domain-Aware Universal Style Transfercited by 40
2021Feature Stylization and Domain-aware Contrastive Learning for Domain Generalizationcited by 40
2022Multi-domain Learning for Updating Face Anti-spoofing Modelscited by 39
2021Language-Driven Image Style Transfercited by 36
2023Neural Preset for Color Style Transfercited by 36
2023Training-free Content Injection using h-space in Diffusion Modelscited by 36
2023HQG-Net: Unpaired Medical Image Enhancement with High-Quality Guidancecited by 36
2023AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networkscited by 34
2024A survey of synthetic data augmentation methods in computer visioncited by 34
2023DiffFashion: Reference-based Fashion Design with Structure-aware Transfer by Diffusion Modelscited by 33
2021Style-Aware Normalized Loss for Improving Arbitrary Style Transfercited by 30
2021PhotoWCT2: Compact Autoencoder for Photorealistic Style Transfer Resulting from Blockwise Training and Skip Connections of High-Frequency Residualscited by 30
2021WaveCNet: Wavelet Integrated CNNs to Suppress Aliasing Effect for Noise-Robust Image Classificationcited by 29
2022Neural Fourier Filter Bankcited by 29
2022DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generationcited by 24
2023CAP-VSTNet: Content Affinity Preserved Versatile Style Transfercited by 24
2022Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learningcited by 23
2022On the Road to Online Adaptation for Semantic Image Segmentationcited by 23
2022Out-of-distribution Detection via Frequency-regularized Generative Modelscited by 23
2023SyreaNet: A Physically Guided Underwater Image Enhancement Framework Integrating Synthetic and Real Imagescited by 23
2022WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generationcited by 22
2024Spectral Motion Alignment for Video Motion Transfer using Diffusion Modelscited by 20
2024Generative Unlearning for Any Identitycited by 19
2022QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelitycited by 18
2021SWAGAN: A Style-based Wavelet-driven Generative Modelcited by 17
2022Image Completion with Heterogeneously Filtered Spectral Hintscited by 17
2024Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learningcited by 17
2022FreGAN: Exploiting Frequency Components for Training GANs under Limited Datacited by 16

50 most cited of 166 All 166 (JSON)