mlsanityData to 7 Oct 2026

EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentation

arXiv 2309.03244 ↗First posted 6 Sep 2023eess.IV cs.CV cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

We introduce EGIC, an enhanced generative image compression method that allows traversing the distortion-perception curve efficiently from a single model. EGIC is based on two novel building blocks: i) OASIS-C, a conditional pre-trained semantic segmentation-guided discriminator, which provides both spatially and semantically-aware gradient feedback to the generator, conditioned on the latent image distribution, and ii) Output Residual Prediction (ORP), a retrofit solution for multi-realism image compression that allows control over the synthesis process by adjusting the impact of the residual between an MSE-optimized and GAN-optimized decoder output on the GAN-based reconstruction. Together, EGIC forms a powerful codec, outperforming state-of-the-art diffusion and GAN-based methods (e.g., HiFiC, MS-ILLM, and DIRAC-100), while performing almost on par with VTM-20.0 on the distortion end. EGIC is simple to implement, very lightweight, and provides excellent interpolation characteristics, which makes it a promising candidate for practical applications targeting the low bit range.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 61 of its 75 references that are in the map. First posted on arXiv 6 Sep 2023.

Builds on

61 of 75 references.

References · 61

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2023Segment Anythingcited by 8,158
  8. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  9. 2017Neural Discrete Representation Learningcited by 4,650
  10. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  11. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  12. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
38 more
  1. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  2. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  3. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  4. 2017Improved Training of Wasserstein GANscited by 2,223
  5. 2014Conditional Generative Adversarial Netscited by 2,152
  6. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  7. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  8. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  9. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  10. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  11. 2016Least Squares Generative Adversarial Networkscited by 1,000
  12. 2018Variational image compression with a scale hyperpriorcited by 910
  13. 2016Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networkscited by 541
  14. 2019Panoptic-DeepLabcited by 362
  15. 2020High-Fidelity Generative Image Compressioncited by 331
  16. 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 296
  17. 2020Channel-wise Autoregressive Entropy Models for Learned Image Compressioncited by 255
  18. 2018cGANs with Projection Discriminatorcited by 253
  19. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 213
  20. 2019Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoffcited by 207
  21. 2020Focal Frequency Loss for Image Reconstruction and Synthesiscited by 204
  22. 2021Projected GANs Converge Fastercited by 204
  23. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 165
  24. 2020You Only Need Adversarial Supervision for Semantic Image Synthesiscited by 129
  25. 2020A U-Net Based Discriminator for Generative Adversarial Networkscited by 128
  26. 2017Real-Time Adaptive Image Compressioncited by 127
  27. 2021ViTGAN: Training GANs with Vision Transformerscited by 110
  28. 2023Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Modelscited by 90
  29. 2022Lossy Compression with Gaussian Diffusioncited by 87
  30. 2022Multi-Realism Image Compression with a Conditional Generatorcited by 79
  31. 2022An Introduction to Neural Data Compressioncited by 78
  32. 2017Learning Convolutional Networks for Content-weighted Image Compressioncited by 73
  33. 2019DeeperLab: Single-Shot Image Parsercited by 63
  34. 2021On the Frequency Bias of Generative Modelscited by 60
  35. 2018Deep Generative Models for Distribution-Preserving Lossy Compressioncited by 59
  36. 2023High-Fidelity Image Compression with Score-based Generative Modelscited by 53
  37. 2018Deep Network Interpolation for Continuous Imagery Effect Transitioncited by 47
  38. 2021Universal Rate-Distortion-Perception Representations for Lossy Compressioncited by 46

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 7; 2026: 5.

13 papers.

Sort:

By area:

  1. 2025StableCodec: Taming One-Step Diffusion for Extreme Image Compressioncited by 29
  2. 2025One-Step Diffusion-Based Image Compression with Semantic Distillationcited by 23
  3. 2024Rate-Distortion-Cognition Controllable Versatile Neural Image Compressioncited by 11
  4. 2025Ultra-Low Bitrate Perceptual Image Compression with Shallow Encodercited by 4
  5. 2026Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compressioncited by 4
  6. 2026CoD-Lite: Real-Time Diffusion-Based Generative Image Compressioncited by 4
  7. 2026DiT-IC: Aligned Diffusion Transformer for Efficient Image Compressioncited by 3
  8. 2026Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priorscited by 2
  9. 2025Hierarchical Semantic Compression for Consistent Image Semantic Restorationcited by 1
  10. 2025PerCoV2: Ultra-Low Bit-Rate Perceptual Image Compression via Query-Based 1D Multimodal Image Tokenscited by 0
  11. 2025Comp-X: On Defining an Interactive Learned Image Compression Paradigm With Expert-driven LLM Agentcited by 0
  12. 2025HyperVQ: Enabling Hyperprior Entropy Modeling for VQ-Based Generative Image Compressioncited by 0
1 more
  1. 2026Group-of-Latents: Perceptual Video Compression at Extreme Bitrates via Masked Latent Generative Modelingcited by 0