mlsanityData to 7 Oct 2026

Generating Images with Perceptual Similarity Metrics based on Deep Networks

arXiv 1602.02644 ↗First posted 8 Feb 2016cs.LG cs.CV cs.NEcited by 221

Not on the map. Why?

Cited by 42 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Image-generating machine learning models are typically trained with loss functions based on distance in the image space. This often leads to over-smoothed results. We propose a class of loss functions, which we call deep perceptual similarity metrics (DeePSiM), that mitigate this problem. Instead of computing distances in the image space, we compute distances between image features extracted by deep neural networks. This metric better reflects perceptually similarity of images and thus leads to better results. We show three applications: autoencoder training, a modification of a variational autoencoder, and inversion of deep convolutional networks. In all cases, the generated images look sharp and resemble natural images.

Key facts. Cited by 221 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Feb 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 59; 2022: 52; 2023: 41; 2024: 28; 2025: 32; 2026: 9.

221 papers.

Sort:

By area:

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  3. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  4. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  5. 2023DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Datacited by 322
  6. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 251
  7. 2022Bridging the Gap to Real-World Object-Centric Learningcited by 219
  8. 2021Projected GANs Converge Fastercited by 204
  9. 2021PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformerscited by 204
  10. 2023Generative Diffusion Prior for Unified Image Restoration and Enhancementcited by 198
  11. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 165
  12. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 157
38 more
  1. 2022FILM: Frame Interpolation for Large Motioncited by 149
  2. 2021ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesiscited by 122
  3. 2021Pixel-wise Anomaly Detection in Complex Driving Scenescited by 109
  4. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  5. 2022DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latentscited by 103
  6. 2024Wonderland: Navigating 3D Scenes from a Single Imagecited by 98
  7. 2021MoFaNeRF: Morphable Facial Neural Radiance Fieldcited by 94
  8. 2025Masked Autoencoders Are Effective Tokenizers for Diffusion Modelscited by 93
  9. 2021Make It Move: Controllable Image-to-Video Generation with Text Descriptionscited by 88
  10. 2021Ensembling Off-the-shelf Models for GAN Trainingcited by 84
  11. 2022An Introduction to Neural Data Compressioncited by 78
  12. 2022Deep Clustering: A Comprehensive Surveycited by 78
  13. 2024Distilling Diffusion Models into Conditional GANscited by 78
  14. 2023VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generationcited by 74
  15. 2024Towards Realistic Scene Generation with LiDAR Diffusion Modelscited by 67
  16. 2021The Spatially-Correlative Loss for Various Image Translation Taskscited by 66
  17. 2023Benchmarking Autoregressive Conditional Diffusion Models for Turbulent Flow Simulationcited by 65
  18. 2021High Fidelity Visualization of What Your Self-Supervised Representation Knows Aboutcited by 64
  19. 2023Anomaly Detection with Conditioned Denoising Diffusion Modelscited by 56
  20. 2024SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizercited by 55
  21. 2021On Aliased Resizing and Surprising Subtleties in GAN Evaluationcited by 51
  22. 2023ControlMat: A Controlled Generative Approach to Material Capturecited by 50
  23. 2021Stochastic Image-to-Video Synthesis using cINNscited by 49
  24. 2023Vector Quantized Time Series Generation with a Bidirectional Prior Modelcited by 49
  25. 2024Adversarial Diffusion Compression for Real-World Image Super-Resolutioncited by 49
  26. 2022Is Geometry Enough for Matching in Visual Localization?cited by 48
  27. 2022Shift-tolerant Perceptual Similarity Metriccited by 44
  28. 2021iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesiscited by 42
  29. 2025DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabulariescited by 42
  30. 2023MatFuse: Controllable Material Generation with Diffusion Modelscited by 39
  31. 2022Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shiftcited by 38
  32. 2024Changen2: Multi-Temporal Remote Sensing Generative Change Foundation Modelcited by 37
  33. 2022Do better ImageNet classifiers assess perceptual similarity better?cited by 34
  34. 2024Heavy-Tailed Diffusion Modelscited by 34
  35. 2024On the Challenges and Opportunities in Generative AIcited by 31
  36. 2021Best-Buddy GANs for Highly Detailed Image Super-Resolutioncited by 30
  37. 2023LD-ZNet: A Latent Diffusion Approach for Text-Based Image Segmentationcited by 29
  38. 2021On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Frameworkcited by 27

50 most cited of 221 All 221 (JSON)