Abstract
Images fed to a deep neural network have in general undergone several handcrafted image signal processing (ISP) operations, all of which have been optimized to produce visually pleasing images. In this work, we investigate the hypothesis that the intermediate representation of visually pleasing images is sub-optimal for downstream computer vision tasks compared to the RAW image representation. We suggest that the operations of the ISP instead should be optimized towards the end task, by learning the parameters of the operations jointly during training. We extend previous works on this topic and propose a new learnable operation that enables an object detector to achieve superior performance when compared to both previous works and traditional RGB images. In experiments on the open PASCALRAW dataset, we empirically confirm our hypothesis.
Abstract (translated)
向深度神经网络输入的图像通常会经历多个手算图像信号处理(ISP)操作,这些操作都已被优化以产生视觉效果良好的图像。在这项工作中,我们探讨了假设,即视觉效果良好的图像的中间表示相对于raw图像表示来说并不是最优的,我们建议ISP的操作应该朝着最终任务进行优化,在训练期间共同学习操作参数。我们扩展了之前关于这个话题的工作,并提出了一个新的可学习操作,它使得物体检测器在与之前工作和传统RGB图像的比较中表现出更好的性能。在开放PASCALRAW数据集的实验中,我们经验证了我们的假设。
URL
https://arxiv.org/abs/2301.08965