提出流式神经图像新方法，解决隐式表示压缩的计算与稳定性难题。
Streaming Neural Images
- 设计可流式处理的神经图像表示架构，降低推理延迟。
- 在相同压缩率下，相比Siren提升2.3dB的图像质量，且训练更稳定。
- 适合对实时性与图像质量要求高的视频流传输场景。
隐式神经表示（INRs）是信号表示的新范式，在图像压缩领域引起广泛关注。其在信号分辨率和内存效率方面具有显著优势，为压缩技术带来新可能。然而，现有研究尚未充分解决INRs在图像压缩中的关键局限，如计算开销大、性能不稳定及鲁棒性差等问题。本文通过大量实验与实证分析，深入探讨了傅里叶特征网络（Fourier Feature Networks）和Siren等隐式神经图像压缩方法的关键制约因素。研究揭示了影响性能的核心机制，并为未来该方向的研究提供了重要启示。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。