An automatic cluster-based approach for depth estimation of single 2D images

In this paper, the problem of single 2D image depth estimation is considered. This is a very important problem due to its various applications in the industry. Previous learning-based methods are based on a key assumption that color images having photometric resemblance are likely to present similar depth structure. However, these methods search the whole dataset for finding corresponding images using handcrafted features, which is quite cumbersome and inefficient process. To overcome this, we have proposed a clustering-based algorithm for depth estimation of a single 2D image using transfer learning. To realize this, images are categorized into clusters using K-means clustering algorithm and features are extracted through a pre-trained deep learning model i.e., ResNet-50. After clustering, an efficient step of replacing feature vector is embedded to speedup the process without compromising on accuracy. After then, images with similar structure as an input image, are retrieved from the best matched cluster based on their correlation values. Then, retrieved candidate depth images are employed to initialize prior depth of a query image using weighted-correlation-average (WCA). Finally, the estimated depth is improved by removing variations using cross-bilateral-filter. In order to evaluate the performance of proposed algorithm, experiments are conducted on two benchmark datasets, NYU v2 and Make3D.