Nowadays, depth estimation from a single 2D image is a prominent task due to its numerous applications such as 2D to 3D image/video conversion, robot vision, and self-driving cars. This research proposes an automatic novel technique for the depth estimation of single 2D images via transfer learning of pre-trained deep learning model. This is a challenging problem, as a single 2D image does not carry any cues regarding depth. To tackle this, the pool of available images is exploited for which the depth is known. By following the hypothesis that the color images having similar semantics are most probably to have similar depth. Along these lines, the depth of the input image is predicted through corresponding depth maps of semantically similar images available in the dataset, fetched by high-level features of pre-trained deep learning model followed by a classifier (i.e., K-Nearest Neighbor). Afterward, a Cross Bilateral filter is applied for the removal of fallacious depth variations in the depth map. To prove the quality of the presented approach, different experiments have been conducted on two publicly available benchmark datasets, NYU (v2) and Make3D. The results indicate that the proposed approach outperforms state of the art methods.
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 learningbased 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 pretrained 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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.