|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
Extensive experiments on the publicly available datasets KITTI, Cityscapes and ApolloScape demonstrate the effectiveness of the proposed model which is competitive with other unsupervised deep learning methods for depth prediction.
In this paper, we first analyse the data distributions and interaction of foreground and background, then propose the foreground-background separated monocular depth estimation (ForeSeE) method, to estimate the foreground depth and background depth using separate optimization objectives and depth decoders.
To this end, we introduce a new Structure-Oriented Memory (SOM) module to learn and memorize the structure-specific information between RGB image domain and the depth domain.
#6 best model for Monocular Depth Estimation on KITTI Eigen split
As deep learning applications are becoming more and more pervasive in robotics, the question of evaluating the reliability of inferences becomes a central question in the robotics community.
Robust three-dimensional scene understanding is now an ever-growing area of research highly relevant in many real-world applications such as autonomous driving and robotic navigation.
Inspired by the success of adversarial learning, we propose a new end-to-end unsupervised deep learning framework for monocular depth estimation consisting of two Generative Adversarial Networks (GAN), deeply coupled with a structured Conditional Random Field (CRF) model.
By viewing the indices as a function of the feature map, we introduce the concept of "learning to index", and present a novel index-guided encoder-decoder framework where indices are self-learned adaptively from data and are used to guide the downsampling and upsampling stages, without extra training supervision.
Estimating depth from a single image represents an attractive alternative to more traditional approaches leveraging multiple cameras.
#3 best model for Monocular Depth Estimation on KITTI Eigen split
In this paper, we address the problem of monocular depth estimation when only a limited number of training image-depth pairs are available.
To this end, we first design a differentiable depth map warping operation, which is end-to-end trainable, and then propose a pose generator to generate novel views for a given image in an adversarial manner.