Papers
Topics
Authors
Recent
Assistant
AI Research Assistant
Well-researched responses based on relevant abstracts and paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses.
Gemini 2.5 Flash
Gemini 2.5 Flash 134 tok/s
Gemini 2.5 Pro 41 tok/s Pro
GPT-5 Medium 40 tok/s Pro
GPT-5 High 38 tok/s Pro
GPT-4o 103 tok/s Pro
Kimi K2 200 tok/s Pro
GPT OSS 120B 438 tok/s Pro
Claude Sonnet 4.5 37 tok/s Pro
2000 character limit reached

Map-Assisted Remote-Sensing Image Compression at Extremely Low Bitrates (2409.01935v1)

Published 3 Sep 2024 in cs.CV

Abstract: Remote-sensing (RS) image compression at extremely low bitrates has always been a challenging task in practical scenarios like edge device storage and narrow bandwidth transmission. Generative models including VAEs and GANs have been explored to compress RS images into extremely low-bitrate streams. However, these generative models struggle to reconstruct visually plausible images due to the highly ill-posed nature of extremely low-bitrate image compression. To this end, we propose an image compression framework that utilizes a pre-trained diffusion model with powerful natural image priors to achieve high-realism reconstructions. However, diffusion models tend to hallucinate small structures and textures due to the significant information loss at limited bitrates. Thus, we introduce vector maps as semantic and structural guidance and propose a novel image compression approach named Map-Assisted Generative Compression (MAGC). MAGC employs a two-stage pipeline to compress and decompress RS images at extremely low bitrates. The first stage maps an image into a latent representation, which is then further compressed in a VAE architecture to save bitrates and serves as implicit guidance in the subsequent diffusion process. The second stage conducts a conditional diffusion model to generate a visually pleasing and semantically accurate result using implicit guidance and explicit semantic guidance. Quantitative and qualitative comparisons show that our method outperforms standard codecs and other learning-based methods in terms of perceptual quality and semantic accuracy. The dataset and code will be publicly available at https://github.com/WHUyyx/MAGC.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (60)
  1. Generative adversarial networks for extreme learned image compression. In Proc. IEEE/CVF Int. Conf. Comput. Vis., pages 221–231, 2019.
  2. Multi-realism image compression with a conditional generator. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., pages 22324–22333, 2023.
  3. End-to-end optimized image compression. In Proc. Int. Conf. Learn. Representat., pages 1–27, 2017.
  4. Variational image compression with a scale hyperprior. In Proc. Int. Conf. Learn. Representat., pages 1–23, 2018.
  5. Compressai: a pytorch library and evaluation platform for end-to-end compression research. arXiv:2011.03029, 2020.
  6. F. Bellard. BPG image format, 2017.
  7. Gisle Bjontegaard. Calculation of average psnr differences between rd-curves. VCEG-M33, 2001.
  8. Rethinking lossy compression: The rate-distortion-perception tradeoff. In Proc. Int. Conf. Mach. Learn., pages 675–685, 2019.
  9. Overview of the versatile video coding (vvc) standard and its applications. IEEE Trans. Circuit Syst. Video Technol., 31(10):3736–3764, 2021.
  10. Towards image compression with perfect realism at ultra-low bitrates. In Proc. Int. Conf. Learn. Representat., pages 1–21, 2023.
  11. Learned image compression with discretized gaussian mixture likelihoods and attention modules. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., pages 7939–7948, 2020.
  12. High-order markov random field as attention network for high-resolution remote-sensing image compression. IEEE Trans. Geosci. Remote Sens., 60:1–14, 2022. Art. no. 5401714.
  13. Satellite image compression and denoising with neural networks. IEEE Geosci. Remote Sens. Lett., 19:1–5, 2022.
  14. Image quality assessment: Unifying structure and texture similarity. IEEE Trans. Pattern Anal. Mach. Intell., 44(5):2567–2581, 2022.
  15. An image is worth 16x16 words: Transformers for image recognition at scale. In Proc. Int. Conf. Learn. Representat., pages 1–21, 2021.
  16. Remote sensing image compression based on the multiple prior information. Remote Sens., 15(8):2211, 2023.
  17. A cartoon-texture approach for jpeg/jpeg 2000 decompression based on tgv and shearlet transform. IEEE Trans. Image Process., 28(3):1356–1365, 2018.
  18. Extending the ccsds recommendation for image data compression for remote sensing scenarios. IEEE Trans. Geosci. Remote Sens., 47(10):3431–3445, 2009.
  19. Jpeg2000 encoding of remote sensing multispectral images with no-data regions. IEEE Geosci. Remote Sens. Lett., 7(2):251–255, 2009.
  20. Generative adversarial nets. In Proc. Adv. Neural Inform. Process. Syst., page 2672–2680, 2014.
  21. Edge-guided remote-sensing image compression. IEEE Trans. Geosci. Remote Sens., 61, 2023. Art. no. 5524515.
  22. Checkerboard context model for efficient learned image compression. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., pages 14771–14780, 2021.
  23. Elic: Efficient learned image compression with unevenly grouped space-channel contextual adaptive coding. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., pages 5718–5727, 2022.
  24. Gans trained by a two time-scale update rule converge to a local nash equilibrium. In Proc. Adv. Neural Inform. Process. Syst., pages 1–12, 2017.
  25. Denoising diffusion probabilistic models. In Proc. Adv. Neural Inform. Process. Syst., pages 6840–6851, 2020.
  26. Fidelity-controllable extreme image compression with generative adversarial networks. In Proc. Int. Conf. Pattern Recognit., pages 8235–8242, 2021.
  27. Generative latent coding for ultra-low bitrate image compression. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., pages 26088–26098, 2024.
  28. Multi-modality deep network for extreme learned image compression. In Proc. AAAI Conf. Artif. Intell., pages 1033–1041, 2023.
  29. Musiq: Multi-scale image quality transformer. In Proc. IEEE/CVF Int. Conf. Comput. Vis., pages 5148–5157, 2021.
  30. Text + sketch: Image compression at ultra low rates. In Proc. Int. Conf. Mach. Learn. Workshop, 2023.
  31. Efficient and effective context-based convolutional entropy modeling for image compression. IEEE Trans. Image Process., 29:5900–5911, 2020.
  32. Learned image compression with mixed transformer-cnn architectures. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., pages 14388–14397, 2023.
  33. A 13.3 gbps 9/7m discrete wavelet transform for ccsds 122.0-b-1 image data compression on a space-grade sram fpga. Electronics, 9(8):1234, 2020.
  34. High-fidelity generative image compression. In Proc. Adv. Neural Inform. Process. Syst., pages 11913–11924, 2020.
  35. Channel-wise autoregressive entropy models for learned image compression. In Proc. IEEE Int. Conf. Image Process., pages 3339–3343, 2020.
  36. Joint autoregressive and hierarchical priors for learned image compression. In Proc. Adv. Neural Inform. Process. Syst., pages 10793–10802, 2018.
  37. T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. In Proc. AAAI Conf. Artif. Intell., pages 4296–4304, 2024.
  38. Improving statistical fidelity for neural image compression with implicit local likelihood models. In Proc. Int. Conf. Mach. Learn., pages 25426–25443, 2023.
  39. A coupled compression generation network for remote-sensing images at extremely low bitrates. IEEE Trans. Geosci. Remote Sens., 61, 2023. Art. no. 5608514.
  40. Extreme generative image compression by learning text embedding from diffusion models. arXiv:2211.07793, 2022.
  41. Semantic image synthesis with spatially-adaptive normalization. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., pages 2337–2346, 2019.
  42. Diffusion autoencoders: Toward a meaningful and decodable representation. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., pages 10619–10629, 2022.
  43. Compressnet: Generative compression at extremely low bitrates. In Proc. IEEE Winter Conf. Appl. Comput. Vis., pages 2325–2333, 2020.
  44. High-resolution image synthesis with latent diffusion models. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., pages 10684–10695, 2022.
  45. Jpeg2000 coding strategies for hyperspectral data. In Proc. IEEE Int. Geosci. Remote Sens. Symp., pages 128–131, 2005.
  46. Generative compression. In Proc. Picture Coding Symp., pages 258–262, 2018.
  47. Joint graph attention and asymmetric convolutional neural network for deep image compression. IEEE Trans. Circuit Syst. Video Technol., 33(1):421–433, 2023.
  48. Jpeg2000: Image compression fundamentals, standards and practice. J. Electron. Imag., 11(2):286–287, 2002.
  49. Lossy image compression with compressive autoencoders. In Proc. Int. Conf. Learn. Representat., pages 1–19, 2022.
  50. G. K. Wallace. The jpeg still picture compression standard. IEEE Trans. Consum. Electron., 38(1):xviii–xxxiv, 1992.
  51. Advancing plain vision transformer toward remote sensing foundation model. IEEE Trans. Geosci. Remote Sens., 61, 2022. Art. no. 5607315.
  52. Uplink-assist downlink remote-sensing image compression via historical referencing. IEEE Trans. Geosci. Remote Sens., 61, 2023. Art. no. 5621415.
  53. Loveda: A remote sensing land-cover dataset for domain adaptive semantic segmentation. arXiv:2110.08733, 2021.
  54. Remote sensing image compression with long-range convolution and improved non-local attention model. Signal Process., 209:109005, 2023.
  55. Remote sensing image compression based on high-frequency and low-frequency components. IEEE Trans. Geosci. Remote Sens., 62, 2024. Art. no. 5604715.
  56. Lossy image compression with conditional diffusion models. In Proc. Adv. Neural Inform. Process. Syst., pages 64971–64995, 2023.
  57. The unreasonable effectiveness of deep features as a perceptual metric. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., pages 586–595, 2018.
  58. Symmetrical lattice generative adversarial network for remote sensing images compression. ISPRS J. Photogramm. and Remote Sens., 176:169–181, 2021.
  59. Transformer-based transform coding. In Proc. Int. Conf. Learn. Representat., pages 1–35, 2022.
  60. The devil is in the details: Window-based attention for image compression. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., pages 17492–17501, 2022.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Dice Question Streamline Icon: https://streamlinehq.com

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up
Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. GitHub - WHUyyx/MAGC: Map-Assisted Remote-Sensing Image Compression at Extremely Low Bitrates (3 stars)