- 博客(0)
- 资源 (3)
- 收藏
- 关注
边缘增强深层网络的图像超分辨率重建
对基于学习的图像超分辨率重建算法中存在边缘信息丢失、易产生视觉伪影等问题,提出一种基 于边缘增强的深层网络模型用于图像的超分辨率重建。方法 本文算法首先利用预处理网络提取输入低分辨率
图像的低级特征,然后将其分别输入到两路网络,其中一路网络通过卷积层级联的卷积网络得到高级特征,另一路 网络通过卷积网络和与卷积网络成镜像结构的反卷积网络的级联实现图像边缘的重建。最后,利用支路连接将两 路网络的结果进行融合,并将其结果通过一个卷积层从而得到最终重建的具有边缘增强效果的高分辨率图像。
结果以峰值信噪比(PSNR)和结构相似度(SSIM)作为评价指标来评价算法性能,在Set5、Setl4和B100等常用测 试集上放大3倍情况下进行实验,并且PSNR/SSIM指标分别取得了33.24 dB/0.9156、30.60 dB/0.852 1和28.45
dB/O.787 3的结果,相比其他方法有很大提升。结论定量与定性的实验结果表明,基于边缘增强的深层网络的 图像超分辨重建算法所重建的高分辨率图像不仅在重建图像边缘信息方面有较好的改善,同时也在客观评价和主 观视觉上都有很大提高。
2018-05-11
Descriptor Learning for Efficient Retrieval
Many visual search and matching systems represent images using sparse sets of “visual words”: descriptors that have been quantized by assignment to the best-matching symbol in a discrete vocabulary. Errors in this quantization procedure propagate throughout the rest of the system, either harming performance or requiring correction using additional storage or processing. This paper aims to reduce these quantization errors at source, by learning a projection from descriptor space to a new Euclidean space in which standard clustering techniques are more likely to assign matching descriptors to the same cluster, and non-matching descriptors to different clusters. To achieve this, we learn a non-linear transformation model by minimizing a novel margin-based cost function, which aims to separate matching descriptors from two classes of non-matching descriptors. Training data is generated automatically by leveraging geometric consistency. Scalable, stochastic gradient methods are used for the optimization. For the case of particular object retrieval, we demonstrate impressive gains in performance on a ground truth dataset: our learnt 32-D descriptor without spatial re-ranking outperforms a baseline method using 128-D SIFT descriptors with spatial re-ranking.
2018-05-11
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人