让图像压缩编码快1000倍，同时保持高压缩效果。
N-O Cool-chic: reconcile fast encoding with lightweight decoding for neural image compression
- 去掉过拟合步骤，用新编码网络替代复杂编码过程。
- 编码复杂度降低1000倍，每像素仅需约2个乘法操作。
- 适合实时应用，兼顾高速与高压缩性能。
过拟合图像编解码器通过为每张图像学习轻量级解码器，实现强压缩性能和低解码复杂度。例如Cool-chic在压缩性能上媲美VVC，且每解码像素仅需约2000次乘法。然而，此类编解码器的编码时间可能过长，难以用于实时场景。本文提出非过拟合（N-O）Cool-chic，通过跳过过拟合过程并引入编码网络，显著降低编码复杂度。相比Cool-chic，N-O Cool-chic将编码复杂度降低1000倍，同时保持竞争力的压缩性能。
原文摘要 · Abstract (English)
Overfitted image codecs achieve strong compression performance and low decoder complexity by learning a lightweight decoder for each image. Such codecs include Cool-chic, which presents image coding performance on par with VVC while requiring around 2000 multiplications per decoded pixel. However, the encoding time associated with overfitted codecs may be prohibitively long for real-time applications, posing a challenge to their practical implementation in such scenarios. To address this issue, this paper proposes to decrease the encoding complexity of Cool-chic by bypassing the overfitting procedure and complementing the decoder with an encoder network. The proposed non-overfitted (N-O) Cool-chic, significantly reduces encoding complexity by a factor of 1000 compared to Cool-chic, while maintaining competitive performance.
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。