Traditional image resizing methods usually work in pixel space and use various saliency measures. The challenge is to adjust the image shape while trying to preserve important content. In this paper we perform image resizing in feature space using the deep layers of a neural network containing rich important semantic information. We directly adjust the image feature maps, extracted from a pre-trained classification network, and reconstruct the resized image using neural-network based optimization. This novel approach leverages the hierarchical encoding of the network, and in particular, the high-level discriminative power of its deeper layers, that can recognize semantic regions and objects, thereby allowing maintenance of their aspect ratios. Our use of reconstruction from deep features results in less noticeable artifacts than use of imagespace resizing operators. We evaluate our method on benchmarks, compare it to alternative approaches, and demonstrate its strengths on challenging images.

传统的图像大小调整方法通常在像素空间中工作，并使用各种显着性度量。挑战在于在尝试保留重要内容的同时调整图像形状。在本文中，我们使用包含丰富的重要语义信息的神经网络的深层在特征空间中执行图像大小调整。我们直接调整图像特征图，从预先训练的分类网络中提取图像，并使用基于神经网络的优化方法重建尺寸调整后的图像。这种新颖的方法利用了网络的分层编码，特别是利用了网络较深层的高级区分能力，可以识别语义区域和对象，从而保持其纵横比。与使用图像空间调整大小运算符相比，我们从深层特征进行重构所产生的伪像更少。我们在基准上评估我们的方法，将其与替代方法进行比较，并展示其在具有挑战性的图像上的优势。