mlsanityData to 7 Oct 2026

PerCo (SD): Open Perceptual Compression

arXiv 2409.20255 ↗First posted 30 Sep 2024cs.CVcited by 16

On the map: Diffusion models → Diffusion for compression and wireless

Abstract (arXiv)

We introduce PerCo (SD), a perceptual image compression method based on Stable Diffusion v2.1, targeting the ultra-low bit range. PerCo (SD) serves as an open and competitive alternative to the state-of-the-art method PerCo, which relies on a proprietary variant of GLIDE and remains closed to the public. In this work, we review the theoretical foundations, discuss key engineering decisions in adapting PerCo to the Stable Diffusion ecosystem, and provide a comprehensive comparison, both quantitatively and qualitatively. On the MSCOCO-30k dataset, PerCo (SD) demonstrates improved perceptual characteristics at the cost of higher distortion. We partly attribute this gap to the different model capacities being used (866M vs. 1.4B). We hope our work contributes to a deeper understanding of the underlying mechanisms and paves the way for future advancements in the field. Code and trained models will be released at https://github.com/Nikolai10/PerCo.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Placed in Diffusion for compression and wireless, one of 14 directions in Diffusion models. Builds on 39 of its 51 references that are in the map. First posted on arXiv 30 Sep 2024.

Builds on

39 of 51 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Lossy Image Compression with Foundation Diffusion Models12 Apr
  2. 2022Extreme Generative Image Compression by Learning Text Embedding from Diffusion Models14 Nov

Other references · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2023GPT-4 Technical Reportcited by 18,132
  7. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  8. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  9. 2020Denoising Diffusion Implicit Modelscited by 9,655
  10. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  11. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  12. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
25 more
  1. 2022Classifier-Free Diffusion Guidancecited by 5,717
  2. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  3. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  4. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  5. 2016Learning without Forgettingcited by 2,465
  6. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  7. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  8. 2018Demystifying MMD GANscited by 1,268
  9. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
  10. 2021Vector-quantized Image Modeling with Improved VQGANcited by 656
  11. 2023Finite Scalar Quantization: VQ-VAE Made Simplecited by 425
  12. 2020High-Fidelity Generative Image Compressioncited by 331
  13. 2023Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discoverycited by 329
  14. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Priorcited by 255
  15. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 213
  16. 2019Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoffcited by 207
  17. 2020You Only Need Adversarial Supervision for Semantic Image Synthesiscited by 129
  18. 2023Towards image compression with perfect realism at ultra-low bitratescited by 99
  19. 2022An Introduction to Neural Data Compressioncited by 78
  20. 2023Text + Sketch: Image Compression at Ultra Low Ratescited by 63
  21. 2018Deep Generative Models for Distribution-Preserving Lossy Compressioncited by 59
  22. 2018Towards Image Understanding from Deep Compression without Decodingcited by 52
  23. 2023If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selectioncited by 40
  24. 2024Consistency-diversity-realism Pareto fronts of conditional image generative modelscited by 35
  25. 2024MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Modelcited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 11; 2026: 5.

16 papers.

Sort:

By area:

  1. 2025StableCodec: Taming One-Step Diffusion for Extreme Image Compressioncited by 29
  2. 2025OSCAR: One-Step Diffusion Codec Across Multiple Bit-ratescited by 24
  3. 2025One-Step Diffusion-Based Image Compression with Semantic Distillationcited by 23
  4. 2025PICD: Versatile Perceptual Image Compression with Diffusion Renderingcited by 10
  5. 2025CoD: A Diffusion Foundation Model for Image Compressioncited by 9
  6. 2025Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compressioncited by 4
  7. 2025Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Priorcited by 4
  8. 2025Ultra-Low Bitrate Perceptual Image Compression with Shallow Encodercited by 4
  9. 2026DiT-IC: Aligned Diffusion Transformer for Efficient Image Compressioncited by 3
  10. 2025Why Compress What You Can Generate? When GPT-4o Generation Ushers in Image Compression Fieldscited by 2
  11. 2026Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priorscited by 2
  12. 2025Hierarchical Semantic Compression for Consistent Image Semantic Restorationcited by 1
4 more
  1. 2025VLIC: Vision-Language Models As Perceptual Judges for Human-Aligned Image Compressioncited by 1
  2. 2026Region-Adaptive Generative Compression with Spatially Varying Diffusion Modelscited by 0
  3. 2026Rethinking Generative Image Compression at Extremely Low Bitratescited by 0
  4. 2026ResARC: Residual-Aware AutoRegressive Coding for Ultra-Low Bitrate Image Compressioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025PerCoV2: Ultra-Low Bit-Rate Perceptual Image Compression via Query-Based 1D Multimodal Image Tokens
  2. 2026One-Step Diffusion for Perceptual Image Compression
  3. 2024Correcting Diffusion-Based Perceptual Image Compression with Privileged End-to-End Decoder
  4. 2025Generative Preprocessing for Image Compression with Pre-trained Diffusion Models
  5. 2025Single-step Diffusion for Image Compression at Ultra-Low Bitrates
  6. 2025DiffVC-OSD: One-Step Diffusion-based Perceptual Neural Video Compression Framework
  7. 2024Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compression
  8. 2025Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion