用低秩表示加速神经图像解码，大幅降低计算开销。
Ultra-Efficient Decoding for End-to-End Neural Compression and Reconstruction
- 在自编码器中引入低秩表示替代复杂卷积解码
- 解码计算量减少，图像重建质量保持高保真
- 适合部署在资源受限设备上的高效压缩系统
图像压缩与重建在各类数字应用中至关重要。尽管当前神经压缩方法已实现优异压缩率，但基于卷积的解码器在数据重建过程中存在复杂度高、计算成本大的问题，限制了技术落地。为解决神经压缩中的解码瓶颈，我们提出一种新框架：在带向量量化（Vector Quantization）的自编码器中引入低秩表示。实验表明，在图像学习到的潜在表示上执行一系列高效的低秩操作，即可实现高质量的数据重建。该方法显著降低了神经压缩/重建中解码阶段的计算开销，基本消除解码计算瓶颈，同时保持图像输出的高保真度。
原文摘要 · Abstract (English)
Image compression and reconstruction are crucial for various digital applications. While contemporary neural compression methods achieve impressive compression rates, the adoption of such technology has been largely hindered by the complexity and large computational costs of the convolution-based decoders during data reconstruction. To address the decoder bottleneck in neural compression, we develop a new compression-reconstruction framework based on incorporating low-rank representation in an autoencoder with vector quantization. We demonstrated that performing a series of computationally efficient low-rank operations on the learned latent representation of images can efficiently reconstruct the data with high quality. Our approach dramatically reduces the computational overhead in the decoding phase of neural compression/reconstruction, essentially eliminating the decoder compute bottleneck while maintaining high fidelity of image outputs.
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。