mlsanityData to 7 Oct 2026

Perceptual Losses for Real-Time Style Transfer and Super-Resolution

arXiv 1603.08155 ↗First posted 27 Mar 2016cs.CV cs.LGcited by 2,678

Not on the map. Why?

Cited by 227 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We consider image transformation problems, where an input image is transformed into an output image. Recent methods for such problems typically train feed-forward convolutional neural networks using a per-pixel loss between the output and ground-truth images. Parallel work has shown that high-quality images can be generated by defining and optimizing perceptual loss functions based on high-level features extracted from pretrained networks. We combine the benefits of both approaches, and propose the use of perceptual loss functions for training feed-forward networks for image transformation tasks. We show results on image style transfer, where a feed-forward network is trained to solve the optimization problem proposed by Gatys et al in real-time. Compared to the optimization-based method, our network gives similar qualitative results but is three orders of magnitude faster. We also experiment with single-image super-resolution, where replacing a per-pixel loss with a perceptual loss gives visually pleasing results.

Key facts. Cited by 2,678 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Mar 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 612; 2022: 570; 2023: 522; 2024: 416; 2025: 331; 2026: 227.

2,678 papers.

Sort:

By area:

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  3. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
  4. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  5. 2021Transformers in Vision: A Surveycited by 1,009
  6. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  7. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  8. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 730
  9. 2022Autoregressive Image Generation using Residual Quantizationcited by 706
  10. 2021Vector-quantized Image Modeling with Improved VQGANcited by 656
  11. 2023GAIA-1: A Generative World Model for Autonomous Drivingcited by 618
  12. 2022Phenaki: Variable Length Video Generation From Open Domain Textual Descriptioncited by 475
38 more
  1. 2023FateZero: Fusing Attentions for Zero-shot Text-based Video Editingcited by 462
  2. 2021GAN Inversion: A Surveycited by 366
  3. 2021Advances in Neural Renderingcited by 365
  4. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 347
  5. 2021Deep ViT Features as Dense Visual Descriptorscited by 327
  6. 2021Rethinking Coarse-to-Fine Approach in Single Image Deblurringcited by 324
  7. 2023DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Datacited by 322
  8. 2022Transformers are Sample-Efficient World Modelscited by 317
  9. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusioncited by 309
  10. 2023Photorealistic Video Generation with Diffusion Modelscited by 304
  11. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  12. 2024An Image is Worth 32 Tokens for Reconstruction and Generationcited by 295
  13. 2023FreeDoM: Training-Free Energy-Guided Conditional Diffusion Modelcited by 290
  14. 2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
  15. 2023Multisample Flow Matching: Straightening Flows with Minibatch Couplingscited by 267
  16. 2021Cross-Modal Contrastive Learning for Text-to-Image Generationcited by 259
  17. 2022Vision Transformers for Single Image Dehazingcited by 255
  18. 2021Motion Representations for Articulated Animationcited by 253
  19. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylizationcited by 251
  20. 2022Visual Prompting via Image Inpaintingcited by 248
  21. 2022Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformercited by 244
  22. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 243
  23. 2023Inpaint Anything: Segment Anything Meets Image Inpaintingcited by 233
  24. 2022Towards Robust Blind Face Restoration with Codebook Lookup Transformercited by 230
  25. 2021HeadNeRF: A Real-time NeRF-based Parametric Head Modelcited by 228
  26. 2021Contrastive Learning for Compact Single Image Dehazingcited by 219
  27. 2022MAT: Mask-Aware Transformer for Large Hole Image Inpaintingcited by 216
  28. 2021Neural Head Avatars from Monocular RGB Videoscited by 212
  29. 2021More Control for Free! Image Synthesis with Semantic Diffusion Guidancecited by 211
  30. 2022Thin-Plate Spline Motion Model for Image Animationcited by 209
  31. 2021Few-shot Image Generation via Cross-domain Correspondencecited by 206
  32. 2021Projected GANs Converge Fastercited by 204
  33. 2021PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformerscited by 204
  34. 2021CLIPstyler: Image Style Transfer with a Single Text Conditioncited by 203
  35. 2021PIRenderer: Controllable Portrait Image Generation via Semantic Neural Renderingcited by 202
  36. 2021GAN Prior Embedded Network for Blind Face Restoration in the Wildcited by 197
  37. 2023ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAscited by 194
  38. 2021StyTr2: Image Style Transfer with Transformerscited by 186

50 most cited of 2,678 All 2,678 (JSON)