用多个专用编码器竞争选择图像区域，实现低复杂度高效压缩。
Spatial Competition for Low-Complexity Learned Image Compression
- 多个专用编码器按区域竞争，选最优方案
- 比单编码器减少14.5%码率，达HEVC水平
- 解码复杂度仅1433 MACs/像素，适合实时应用
基于自编码器的图像编码器虽达到顶尖压缩性能，但通常计算复杂度高，尤其在解码阶段。本文提出一种基于多个专用神经编码器空间竞争的低复杂度学习式图像压缩框架。每个图像区域由编码器根据率失真代价选择最匹配内容的编码器，通过传输模式图作为侧信息指示区域选择结果。解码时，该模式图指导重建，同时保持单个编码器的复杂度。此设计实现了每图像自适应且解码复杂度低、编码速度快。在CLIC 2020数据集上，本方法相较单编码器最多降低14.5%码率，并以1433 MACs/像素的解码复杂度达到HEVC级别性能。
原文摘要 · Abstract (English)
Autoencoder-based image codecs achieve state-of-the-art compression performance but often incur high computational complexity, particularly at decoding time. This work introduces a low-complexity learned image compression framework based on spatial competition between multiple specialized neural codecs. For each image region, the encoder selects the codec that best matches the local content according to a rate-distortion cost. A mode map is transmitted as side information to indicate the per-region codec selection. At decoding time, this mode map-based selection guides reconstruction while preserving the complexity of a single codec. This design enables per-image adaptation with low decoding complexity and fast encoding. On the CLIC 2020 dataset, our method achieves up to -14.5% rate reduction compared to a single codec and reaches HEVC-level performance with a decoding complexity of 1433 MACs per pixel.
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。