Abstract
Neural image codecs achieve higher compression ratios than traditional hand-crafted methods such as PNG or JPEG-XL, but often incur substantial computational overhead, limiting their deployment on energy-constrained devices such as smartphones, cameras, and drones. We propose Grayscale Image Compression with Differentiable Logic Circuits (GIC-DLC), a hardware-aware codec where we train lookup tables to combine the flexibility of neural networks with the efficiency of Boolean operations. Experiments on grayscale benchmark datasets show that GIC-DLC outperforms traditional codecs in compression efficiency while allowing substantial reductions in energy consumption and latency. These results demonstrate that learned compression can be hardware-friendly, offering a promising direction for low-power image compression on edge devices.
Abstract (translated)
神经图像编解码器比传统的手工设计方法（如PNG或JPEG-XL）实现了更高的压缩比率，但通常会带来显著的计算开销，限制了它们在智能手机、相机和无人机等能量受限设备上的部署。我们提出了灰度图像压缩与可微逻辑电路 (GIC-DLC)，这是一种硬件感知编解码器，我们在其中训练查找表以结合神经网络的灵活性和布尔运算的效率。在灰度基准数据集上的实验表明，GIC-DLC 在压缩效率上超越了传统编解码器，并且能够在很大程度上减少能量消耗和延迟。这些结果证明了学习到的压缩技术可以是硬件友好的，为边缘设备上的低功耗图像压缩提供了一个有前景的方向。
URL
https://arxiv.org/abs/2601.14130
