用插值量化缩小查找表，让图像超分辨率更快更省空间。
IQ-LUT: interpolated and quantized LUT for efficient image super-resolution
- 将插值与量化结合到ECNN中，大幅压缩索引空间。
- 存储量减少50倍，同时提升细节重建质量。
- 适合部署在内存受限设备的高效超分模型。
查找表（LUT）方法在加速图像超分辨率推理方面展现出巨大潜力。然而，为追求更高图像质量而增大感受野和位深度会导致LUT索引空间呈指数级增长，形成存储瓶颈，限制其在资源受限设备上的部署。本文提出IQ-LUT，实现LUT尺寸减小的同时提升超分辨率质量。首先，将插值与量化集成到单输入多输出的ECNN中，显著压缩索引空间，从而降低整体LUT大小。其次，引入残差学习减轻对LUT位深度的依赖，提升训练稳定性，并更关注细微结构的重建，带来更好的视觉效果。最后，基于知识蒸馏设计非均匀量化策略，优化量化级别，在减少存储开销的同时补偿量化损失。大量基准测试表明，该方法相比ECNN可将存储成本降低最多50倍，同时实现更优的超分辨率质量。
原文摘要 · Abstract (English)
Lookup table (LUT) methods demonstrate considerable potential in accelerating image super-resolution inference. However, pursuing higher image quality through larger receptive fields and bit-depth triggers exponential growth in the LUT's index space, creating a storage bottleneck that limits deployment on resource-constrained devices. We introduce IQ-LUT, which achieves a reduction in LUT size while simultaneously enhancing super-resolution quality. First, we integrate interpolation and quantization into the single-input, multiple-output ECNN, which dramatically reduces the index space and thereby the overall LUT size. Second, the integration of residual learning mitigates the dependence on LUT bit-depth, which facilitates training stability and prioritizes the reconstruction of fine-grained details for superior visual quality. Finally, guided by knowledge distillation, our non-uniform quantization process optimizes the quantization levels, thereby reducing storage while also compensating for quantization loss. Extensive benchmarking demonstrates our approach substantially reduces storage costs (by up to 50x compared to ECNN) while achieving superior super-resolution quality.
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。