mlsanityData to 7 Oct 2026

Streaming Neural Images

arXiv 2409.17134 ↗First posted 25 Sep 2024cs.CV eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

Implicit Neural Representations (INRs) are a novel paradigm for signal representation that have attracted considerable interest for image compression. INRs offer unprecedented advantages in signal resolution and memory efficiency, enabling new possibilities for compression techniques. However, the existing limitations of INRs for image compression have not been sufficiently addressed in the literature. In this work, we explore the critical yet overlooked limiting factors of INRs, such as computational cost, unstable performance, and robustness. Through extensive experiments and empirical analysis, we provide a deeper and more nuanced understanding of implicit neural image compression methods such as Fourier Feature Networks and Siren. Our work also offers valuable insights for future research in this area.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 26 references that are in the map. First posted on arXiv 25 Sep 2024.

Builds on

18 of 26 references.

References · 18

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  3. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  4. 2016Deep Networks with Stochastic Depthcited by 973
  5. 2018Variational image compression with a scale hyperpriorcited by 910
  6. 2020High-Fidelity Generative Image Compressioncited by 331
  7. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 240
  8. 2021COIN: COmpression with Implicit Neural representationscited by 232
  9. 2023WIRE: Wavelet Implicit Neural Representationscited by 220
  10. 2021Implicit Neural Representations for Image Compressioncited by 161
  11. 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 142
  12. 2017Real-Time Adaptive Image Compressioncited by 127
6 more
  1. 2022COIN++: Neural Compression Across Modalitiescited by 81
  2. 2022Transformers as Meta-Learners for Implicit Neural Representationscited by 79
  3. 2021Meta-Learning Sparse Implicit Neural Representationscited by 48
  4. 2022DINER: Disorder-Invariant Implicit Neural Representationcited by 30
  5. 2022Streamable Neural Fieldscited by 13
  6. 2024Extreme Compression of Adaptive Neural Imagescited by 1

Built on by

Not cited yet.