No Arabic abstract
Previous unsupervised monocular depth estimation methods mainly focus on the day-time scenario, and their frameworks are driven by warped photometric consistency. While in some challenging environments, like night, rainy night or snowy winter, the photometry of the same pixel on different frames is inconsistent because of the complex lighting and reflection, so that the day-time unsupervised frameworks cannot be directly applied to these complex scenarios. In this paper, we investigate the problem of unsupervised monocular depth estimation in certain highly complex scenarios. We address this challenging problem by using domain adaptation, and a unified image transfer-based adaptation framework is proposed based on monocular videos in this paper. The depth model trained on day-time scenarios is adapted to different complex scenarios. Instead of adapting the whole depth network, we just consider the encoder network for lower computational complexity. The depth models adapted by the proposed framework to different scenarios share the same decoder, which is practical. Constraints on both feature space and output space promote the framework to learn the key features for depth decoding, and the smoothness loss is introduced into the adaptation framework for better depth estimation performance. Extensive experiments show the effectiveness of the proposed unsupervised framework in estimating the dense depth map from the night-time, rainy night-time and snowy winter images.
In recent years, unsupervised deep learning approaches have received significant attention to estimate the depth and visual odometry (VO) from unlabelled monocular image sequences. However, their performance is limited in challenging environments due to perceptual degradation, occlusions and rapid motions. Moreover, the existing unsupervised methods suffer from the lack of scale-consistency constraints across frames, which causes that the VO estimators fail to provide persistent trajectories over long sequences. In this study, we propose an unsupervised monocular deep VO framework that predicts six-degrees-of-freedom pose camera motion and depth map of the scene from unlabelled RGB image sequences. We provide detailed quantitative and qualitative evaluations of the proposed framework on a) a challenging dataset collected during the DARPA Subterranean challenge; and b) the benchmark KITTI and Cityscapes datasets. The proposed approach outperforms both traditional and state-of-the-art unsupervised deep VO methods providing better results for both pose estimation and depth recovery. The presented approach is part of the solution used by the COSTAR team participating at the DARPA Subterranean Challenge.
We propose a semantics-driven unsupervised learning approach for monocular depth and ego-motion estimation from videos in this paper. Recent unsupervised learning methods employ photometric errors between synthetic view and actual image as a supervision signal for training. In our method, we exploit semantic segmentation information to mitigate the effects of dynamic objects and occlusions in the scene, and to improve depth prediction performance by considering the correlation between depth and semantics. To avoid costly labeling process, we use noisy semantic segmentation results obtained by a pre-trained semantic segmentation network. In addition, we minimize the position error between the corresponding points of adjacent frames to utilize 3D spatial information. Experimental results on the KITTI dataset show that our method achieves good performance in both depth and ego-motion estimation tasks.
In this paper, we address the problem of monocular depth estimation when only a limited number of training image-depth pairs are available. To achieve a high regression accuracy, the state-of-the-art estimation methods rely on CNNs trained with a large number of image-depth pairs, which are prohibitively costly or even infeasible to acquire. Aiming to break the curse of such expensive data collections, we propose a semi-supervised adversarial learning framework that only utilizes a small number of image-depth pairs in conjunction with a large number of easily-available monocular images to achieve high performance. In particular, we use one generator to regress the depth and two discriminators to evaluate the predicted depth , i.e., one inspects the image-depth pair while the other inspects the depth channel alone. These two discriminators provide their feedbacks to the generator as the loss to generate more realistic and accurate depth predictions. Experiments show that the proposed approach can (1) improve most state-of-the-art models on the NYUD v2 dataset by effectively leveraging additional unlabeled data sources; (2) reach state-of-the-art accuracy when the training set is small, e.g., on the Make3D dataset; (3) adapt well to an unseen new dataset (Make3D in our case) after training on an annotated dataset (KITTI in our case).
We present a novel method to train machine learning algorithms to estimate scene depths from a single image, by using the information provided by a cameras aperture as supervision. Prior works use a depth sensors outputs or images of the same scene from alternate viewpoints as supervision, while our method instead uses images from the same viewpoint taken with a varying camera aperture. To enable learning algorithms to use aperture effects as supervision, we introduce two differentiable aperture rendering functions that use the input image and predicted depths to simulate the depth-of-field effects caused by real camera apertures. We train a monocular depth estimation network end-to-end to predict the scene depths that best explain these finite aperture images as defocus-blurred renderings of the input all-in-focus image.
In the recent years, many methods demonstrated the ability of neural networks tolearn depth and pose changes in a sequence of images, using only self-supervision as thetraining signal. Whilst the networks achieve good performance, the often over-lookeddetail is that due to the inherent ambiguity of monocular vision they predict depth up to aunknown scaling factor. The scaling factor is then typically obtained from the LiDARground truth at test time, which severely limits practical applications of these methods.In this paper, we show that incorporating prior information about the camera configu-ration and the environment, we can remove the scale ambiguity and predict depth directly,still using the self-supervised formulation and not relying on any additional sensors.