mlsanityData to 7 Oct 2026

Neural-based Video Compression on Solar Dynamics Observatory Images

arXiv 2407.15730 ↗First posted 12 Jul 2024eess.IV astro-ph.IM cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

NASA's Solar Dynamics Observatory (SDO) mission collects extensive data to monitor the Sun's daily activity. In the realm of space mission design, data compression plays a crucial role in addressing the challenges posed by limited telemetry rates. The primary objective of data compression is to facilitate efficient data management and transmission to work within the constrained bandwidth, thereby ensuring that essential information is captured while optimizing the utilization of available resources. This paper introduces a neural video compression technique that achieves a high compression ratio for the SDO's image data collection. The proposed approach focuses on leveraging both temporal and spatial redundancies in the data, leading to a more efficient compression. In this work, we introduce an architecture based on the Transformer model, which is specifically designed to capture both local and global information from input images in an effective and efficient manner. Additionally, our network is equipped with an entropy model that can accurately model the probability distribution of the latent representations and improves the speed of the entropy decoding step. The entropy model leverages a channel-dependent approach and utilizes checkerboard-shaped local and global spatial contexts. By combining the Transformer-based video compression network with our entropy model, the proposed compression algorithm demonstrates superior performance over traditional video codecs like H.264 and H.265, as confirmed by our experimental results.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 62 of its 88 references that are in the map. First posted on arXiv 12 Jul 2024.

Builds on

62 of 88 references.

References · 62

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  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. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2022Generative Adversarial Networkscited by 5,603
  8. 2017Squeeze-and-Excitation Networkscited by 4,763
  9. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  10. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  11. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  12. 2018Variational image compression with a scale hyperpriorcited by 910
38 more
  1. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  2. 2016End-to-end Optimized Image Compressioncited by 673
  3. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  4. 2020End-to-End Video Instance Segmentation with Transformerscited by 443
  5. 2016Optical Flow Estimation using a Spatial Pyramid Networkcited by 421
  6. 2020MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformerscited by 355
  7. 2020High-Fidelity Generative Image Compressioncited by 331
  8. 2018DVC: An End-to-end Deep Video Compression Frameworkcited by 324
  9. 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 296
  10. 2021Post-Training Quantization for Vision Transformercited by 274
  11. 2020Channel-wise Autoregressive Entropy Models for Learned Image Compressioncited by 255
  12. 2021Checkerboard Context Model for Efficient Learned Image Compressioncited by 193
  13. 2021Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformercited by 175
  14. 2021PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantizationcited by 173
  15. 2017Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representationscited by 149
  16. 2021FVC: A New Framework towards Deep Video Compression in Feature Spacecited by 149
  17. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  18. 2018Video Compression through Image Interpolationcited by 143
  19. 2018Context-adaptive Entropy Model for End-to-end Optimized Image Compressioncited by 138
  20. 2020Nonlinear Transform Codingcited by 132
  21. 2020End-to-End Object Detection with Adaptive Clustering Transformercited by 109
  22. 2020M-LVC: Multiple Frames Prediction for Learned Video Compressioncited by 106
  23. 2022Entroformer: A Transformer-based Entropy Model for Learned Image Compressioncited by 102
  24. 2019Video Compression With Rate-Distortion Autoencoderscited by 97
  25. 2020Learning for Video Compression with Hierarchical Quality and Recurrent Enhancementcited by 90
  26. 2018Learned Video Compressioncited by 89
  27. 2021Scalable Vision Transformers with Hierarchical Poolingcited by 84
  28. 2019Image and Video Compression with Neural Networks: A Reviewcited by 82
  29. 2022Multi-Realism Image Compression with a Conditional Generatorcited by 79
  30. 2022An Introduction to Neural Data Compressioncited by 78
  31. 2022VCT: A Video Compression Transformercited by 74
  32. 2016End-to-end optimization of nonlinear transform codes for perceptual qualitycited by 72
  33. 2021ELF-VC: Efficient Learned Flexible-Rate Video Codingcited by 68
  34. 2022DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformerscited by 65
  35. 2021Learning Efficient Vision Transformers via Fine-Grained Manifold Distillationcited by 60
  36. 2020FTRANS: Energy-Efficient Acceleration of Transformers using FPGAcited by 52
  37. 2021Soft then Hard: Rethinking the Quantization in Neural Image Compressioncited by 50
  38. 2020Conditional Entropy Coding for Efficient Video Compressioncited by 42

50 most cited of 62 All 62 (JSON)

Built on by

Not cited yet.