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 where the deep layers of a neural network contain rich important semantic information. We directly adjust the image feature maps, extracted from a pre-trained classification network, and reconstruct the resized image using a 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 recognizes semantic objects and regions and allows maintaining their aspect ratio. Our use of reconstruction from deep features diminishes the artifacts introduced by image-space resizing operators. We evaluate our method on benchmarks, compare to alternative approaches, and demonstrate its strength on challenging images.
翻译:传统图像调整方法通常在像素空间中发挥作用,并使用各种突出的尺度。 挑战在于调整图像形状,同时努力保存重要内容。 在本文中,我们在神经网络深层包含丰富的重要语义信息的特征空间中进行图像调整。 我们直接调整图像特征图,从预先培训的分类网络中提取,并利用神经网络优化来重建重新缩放图像。 这种创新方法利用网络的等级编码,特别是其深层的高层次歧视性力量,承认语义物体和地区,并允许保持其侧面比。 我们利用深层特征的重建减少了图像空间调整操作者引入的文物。 我们评估了我们的基准方法,比较了其他方法,并展示了其在具有挑战性图像上的力量。