# Ultrafast Photorealistic Style Transfer via Neural Architecture Search

arXiv: https://arxiv.org/abs/1912.02398 · HTML: https://mlsanity.com/paper/1912.02398/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2019.

## Built on by (most cited first, 30 of 39)

- [StyTr2: Image Style Transfer with Transformers](https://mlsanity.com/paper/2105.14576/) (2021)
- [ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows](https://mlsanity.com/paper/2103.16877/) (2021)
- [Domain-Aware Universal Style Transfer](https://mlsanity.com/paper/2108.04441/) (2021)
- [Neural Preset for Color Style Transfer](https://mlsanity.com/paper/2303.13511/) (2023)
- [AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks](https://mlsanity.com/paper/2307.09724/) (2023)
- [PhotoWCT2: Compact Autoencoder for Photorealistic Style Transfer Resulting from Blockwise Training and Skip Connections of High-Frequency Residuals](https://mlsanity.com/paper/2110.11995/) (2021)
- [EleGANt: Exquisite and Locally Editable GAN for Makeup Transfer](https://mlsanity.com/paper/2207.09840/) (2022)
- [CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer](https://mlsanity.com/paper/2303.17867/) (2023)
- [On the Road to Online Adaptation for Semantic Image Segmentation](https://mlsanity.com/paper/2203.16195/) (2022)
- [QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity](https://mlsanity.com/paper/2212.10431/) (2022)
- [Facial Attribute Transformers for Precise and Robust Makeup Transfer](https://mlsanity.com/paper/2104.02894/) (2021)
- [Z^*: Zero-shot Style Transfer via Attention Rearrangement](https://mlsanity.com/paper/2311.16491/) (2023)
- [S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attention](https://mlsanity.com/paper/2210.12381/) (2022)
- [PCA-Based Knowledge Distillation Towards Lightweight and Content-Style Balanced Photorealistic Style Transfer Models](https://mlsanity.com/paper/2203.13452/) (2022)
- [Learning to Evaluate the Artness of AI-generated Images](https://mlsanity.com/paper/2305.04923/) (2023)
- [Color Conditional Generation with Sliced Wasserstein Guidance](https://mlsanity.com/paper/2503.19034/) (2025)
- [Video Color Grading via Look-Up Table Generation](https://mlsanity.com/paper/2508.00548/) (2025)
- [Deep Translation Prior: Test-time Training for Photorealistic Style Transfer](https://mlsanity.com/paper/2112.06150/) (2021)
- [Contrastive Learning for Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2105.03117/) (2021)
- [AdaCM: Adaptive ColorMLP for Real-Time Universal Photo-realistic Style Transfer](https://mlsanity.com/paper/2212.01567/) (2022)
- [Color Transfer with Modulated Flows](https://mlsanity.com/paper/2503.19062/) (2025)
- [Color Prompting for Data-Free Continual Unsupervised Domain Adaptive Person Re-Identification](https://mlsanity.com/paper/2308.10716/) (2023)
- [Modernizing Old Photos Using Multiple References via Photorealistic Style Transfer](https://mlsanity.com/paper/2304.04461/) (2023)
- [Evaluation in Neural Style Transfer: A Review](https://mlsanity.com/paper/2401.17109/) (2024)
- [StyleFlow For Content-Fixed Image to Image Translation](https://mlsanity.com/paper/2207.01909/) (2022)
- [INRetouch: Context Aware Implicit Neural Representation for Photography Retouching](https://mlsanity.com/paper/2412.03848/) (2024)
- [Neural Style Transfer for Computer Games](https://mlsanity.com/paper/2311.14617/) (2023)
- [Level generation and style enhancement -- deep learning for game development overview](https://mlsanity.com/paper/2107.07397/) (2021)
- [Optimal Image Transport on Sparse Dictionaries](https://mlsanity.com/paper/2311.01984/) (2023)
- [Towards In-Context Tone Style Transfer with A Large-Scale Triplet Dataset](https://mlsanity.com/paper/2604.16114/) (2026)

## Abstract (arXiv)

The key challenge in photorealistic style transfer is that an algorithm should faithfully transfer the style of a reference photo to a content photo while the generated image should look like one captured by a camera. Although several photorealistic style transfer algorithms have been proposed, they need to rely on post- and/or pre-processing to make the generated images look photorealistic. If we disable the additional processing, these algorithms would fail to produce plausible photorealistic stylization in terms of detail preservation and photorealism. In this work, we propose an effective solution to these issues. Our method consists of a construction step (C-step) to build a photorealistic stylization network and a pruning step (P-step) for acceleration. In the C-step, we propose a dense auto-encoder named PhotoNet based on a carefully designed pre-analysis. PhotoNet integrates a feature aggregation module (BFA) and instance normalized skip links (INSL). To generate faithful stylization, we introduce multiple style transfer modules in the decoder and INSLs. PhotoNet significantly outperforms existing algorithms in terms of both efficiency and effectiveness. In the P-step, we adopt a neural architecture search method to accelerate PhotoNet. We propose an automatic network pruning framework in the manner of teacher-student learning for photorealistic stylization. The network architecture named PhotoNAS resulted from the search achieves significant acceleration over PhotoNet while keeping the stylization effects almost intact. We conduct extensive experiments on both image and video transfer. The results show that our method can produce favorable results while achieving 20-30 times acceleration in comparison with the existing state-of-the-art approaches. It is worth noting that the proposed algorithm accomplishes better performance without any pre- or post-processing.