We propose a convolutional neural network (ConvNet) based approach for
learning local image descriptors which can be used for significantly improved
patch matching and 3D reconstructions. A multi-resolution ConvNet is used for
learning keypoint descriptors. We also propose a new dataset consisting of an
order of magnitude more number of scenes, images, and positive and negative
correspondences compared to the currently available Multi-View Stereo (MVS)
[18] dataset. The new dataset also has better coverage of the overall
viewpoint, scale, and lighting changes in comparison to the MVS dataset. We
evaluate our approach on publicly available datasets, such as Oxford Affine
Covariant Regions Dataset (ACRD) [12], MVS [18], Synthetic [6] and Strecha [15]
datasets to quantify the image descriptor performance. Scenes from the Oxford
ACRD, MVS and Synthetic datasets are used for evaluating the patch matching
performance of the learnt descriptors while the Strecha dataset is used to
evaluate the 3D reconstruction task. Experiments show that the proposed
descriptor outperforms the current state-of-the-art descriptors in both the
evaluation tasks.

提出了一种基于卷积神经网络 (ConvNet) 的方法，用于学习本地图像描述符，可用于显着改善补丁匹配和三维重建，该方法使用多分辨率 ConvNets 学习关键点描述符，并且提出了一个新的数据集，包含比当前可用的 Multi-View Stereo（MVS）数据集更多的图像和正负对应物，并且在视角，尺度和光照变化方面具有更好的覆盖范围。该文对基于提出的描述符学习的补丁匹配和三维重建任务进行了评估，实验结果表明，在评价任务中，提出的描述符优于当前现有的最先进描述符。