Related papers: Learning Depth via Leveraging Semantics: Self-supe…
Autonomous vehicles and robots require a full scene understanding of the environment to interact with it. Such a perception typically incorporates pixel-wise knowledge of the depths and semantic labels for each image from a video sensor.…
Monocular depth estimation in the wild inherently predicts depth up to an unknown scale. To resolve scale ambiguity issue, we present a learning algorithm that leverages monocular simultaneous localization and mapping (SLAM) with…
Depth completion is an important vision task, and many efforts have been made to enhance the quality of depth maps from sparse depth measurements. Despite significant advances, training these models to recover dense depth from sparse…
3D semantic scene understanding is a fundamental challenge in computer vision. It enables mobile agents to autonomously plan and navigate arbitrary environments. SSC formalizes this challenge as jointly estimating dense geometry and…
The ability to accurately estimate depth information is crucial for many autonomous applications to recognize the surrounded environment and predict the depth of important objects. One of the most recently used techniques is monocular depth…
Scene depth estimation from stereo and monocular imagery is critical for extracting 3D information for downstream tasks such as scene understanding. Recently, learning-based methods for depth estimation have received much attention due to…
While depth sensors are becoming increasingly popular, their spatial resolution often remains limited. Depth super-resolution therefore emerged as a solution to this problem. Despite much progress, state-of-the-art techniques suffer from…
Robust geometric and semantic scene understanding is ever more important in many real-world applications such as autonomous driving and robotic navigation. In this paper, we propose a multi-task learning-based approach capable of jointly…
For monocular depth estimation, acquiring ground truths for real data is not easy, and thus domain adaptation methods are commonly adopted using the supervised synthetic data. However, this may still incur a large domain gap due to the lack…
Depth information is important for autonomous systems to perceive environments and estimate their own state. Traditional depth estimation methods, like structure from motion and stereo vision matching, are built on feature correspondences…
Neural networks have shown great success in extracting geometric information from color images. Especially, monocular depth estimation networks are increasingly reliable in real-world scenes. In this work we investigate the applicability of…
This paper proposes to use keypoints as a self-supervision clue for learning depth map estimation from a collection of input images. As ground truth depth from real images is difficult to obtain, there are many unsupervised and…
In this paper we consider the problem of single monocular image depth estimation. It is a challenging problem due to its ill-posedness nature and has found wide application in industry. Previous efforts belongs roughly to two families:…
Due to the lack of extensive precisely-annotated multi-label data in real word, semi-supervised multi-label learning (SSMLL) has gradually gained attention. Abundant knowledge embedded in vision-language models (VLMs) pre-trained on…
Depth estimation from single monocular images is a key component of scene understanding and has benefited largely from deep convolutional neural networks (CNN) recently. In this article, we take advantage of the recent deep residual…
Although recent semantic segmentation methods have made remarkable progress, they still rely on large amounts of annotated training data, which are often infeasible to collect in the autonomous driving scenario. Previous works usually…
There has been tremendous research progress in estimating the depth of a scene from a monocular camera image. Existing methods for single-image depth prediction are exclusively based on deep neural networks, and their training can be…
Supervised learning based methods for monocular depth estimation usually require large amounts of extensively annotated training data. In the case of aerial imagery, this ground truth is particularly difficult to acquire. Therefore, in this…
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. In this paper, we propose a multi-task learning-based…
Recently, contrastive learning has largely advanced the progress of unsupervised visual representation learning. Pre-trained on ImageNet, some self-supervised algorithms reported higher transfer learning performance compared to…