mlsanityData to 7 Oct 2026

PyramidStyler: Transformer-Based Neural Style Transfer with Pyramidal Positional Encoding and Reinforcement Learning

arXiv 2510.01715 ↗First posted 2 Oct 2025cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Neural Style Transfer (NST) has evolved from Gatys et al.'s (2015) CNN-based algorithm, enabling AI-driven artistic image synthesis. However, existing CNN and transformer-based models struggle to scale efficiently to complex styles and high-resolution inputs. We introduce PyramidStyler, a transformer framework with Pyramidal Positional Encoding (PPE): a hierarchical, multi-scale encoding that captures both local details and global context while reducing computational load. We further incorporate reinforcement learning to dynamically optimize stylization, accelerating convergence. Trained on Microsoft COCO and WikiArt, PyramidStyler reduces content loss by 62.6% (to 2.07) and style loss by 57.4% (to 0.86) after 4000 epochs--achieving 1.39 s inference--and yields further improvements (content 2.03; style 0.75) with minimal speed penalty (1.40 s) when using RL. These results demonstrate real-time, high-quality artistic rendering, with broad applications in media and design.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 29 references that are in the map. First posted on arXiv 2 Oct 2025.

Builds on

24 of 29 references.

References · 24

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  7. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  8. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  9. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  10. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  11. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  12. 2018Self-Attention with Relative Position Representationscited by 1,112
12 more
  1. 2020Pre-Trained Image Processing Transformercited by 891
  2. 2020End-to-End Video Instance Segmentation with Transformerscited by 443
  3. 2017Universal Style Transfer via Feature Transformscited by 352
  4. 2016A Learned Representation For Artistic Stylecited by 340
  5. 2020Visual Transformers: Token-based Image Representation and Processing for Computer Visioncited by 333
  6. 2018Arbitrary Style Transfer with Style-Attentional Networkscited by 197
  7. 2016Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networkscited by 192
  8. 2021Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformercited by 175
  9. 2020How Much Position Information Do Convolutional Neural Networks Encode?cited by 171
  10. 2017StyleBank: An Explicit Representation for Neural Image Style Transfercited by 89
  11. 2020Positional Encoding as Spatial Inductive Bias in GANscited by 69
  12. 2020Distribution Aligned Multimodal and Multi-Domain Image Stylizationcited by 10

Built on by

Not cited yet.