论文标题
用于计算高效的移动逆音映射的混合量化网络
A Mixed Quantization Network for Computationally Efficient Mobile Inverse Tone Mapping
论文作者
论文摘要
从单个低动态范围（LDR）图像（即反向音调映射（ITM））中恢复高动态范围（HDR）图像，这是由于缺乏过度和暴露不足的区域中的信息而挑战。当前的方法仅着重于培训高性能但计算效率低下的ITM模型，这反过来妨碍了ITM模型在资源受限环境中的部署，具有有限的计算能力，例如Edge和移动设备应用程序。 为此，我们建议将深神网络的有效操作与新型混合量化方案相结合，以构建一个表现良好但有效的混合量化网络（MQN），该网络（MQN）可以在移动平台上执行单个图像ITM。在消融研究中，我们探讨了使用不同注意机制，量化方案和损失函数对ITM任务中MQN性能的影响。在比较分析中，使用MQN训练的ITM模型与基准数据集上的最先进方法进行了训练。 MQN型号可改善潜伏期的10倍，并改善25倍的记忆消耗。
Recovering a high dynamic range (HDR) image from a single low dynamic range (LDR) image, namely inverse tone mapping (ITM), is challenging due to the lack of information in over- and under-exposed regions. Current methods focus exclusively on training high-performing but computationally inefficient ITM models, which in turn hinder deployment of the ITM models in resource-constrained environments with limited computing power such as edge and mobile device applications. To this end, we propose combining efficient operations of deep neural networks with a novel mixed quantization scheme to construct a well-performing but computationally efficient mixed quantization network (MQN) which can perform single image ITM on mobile platforms. In the ablation studies, we explore the effect of using different attention mechanisms, quantization schemes, and loss functions on the performance of MQN in ITM tasks. In the comparative analyses, ITM models trained using MQN perform on par with the state-of-the-art methods on benchmark datasets. MQN models provide up to 10 times improvement on latency and 25 times improvement on memory consumption.
