Related papers: On depth prediction for autonomous driving using s…

Self-supervised monocular depth estimation is a salient task for 3D scene understanding. Learned jointly with monocular ego-motion estimation, several methods have been proposed to predict accurate pixel-wise depth without using labeled…

Depth estimation is a traditional computer vision task, which plays a crucial role in understanding 3D scene geometry. Recently, deep-convolutional-neural-networks based methods have achieved promising results in the monocular depth…

Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training models to perform monocular depth estimation. In this paper, we…

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.…

Generalizing metric monocular depth estimation presents a significant challenge due to its ill-posed nature, while the entanglement between camera parameters and depth amplifies issues further, hindering multi-dataset training and zero-shot…

This paper focuses on self-supervised monocular depth estimation in dynamic scenes trained on monocular videos. Existing methods jointly estimate pixel-wise depth and motion, relying mainly on an image reconstruction loss. Dynamic regions1…

Self-supervised monocular depth estimation (MDE) has gained popularity for obtaining depth predictions directly from videos. However, these methods often produce scale invariant results, unless additional training signals are provided.…

With the rapid advancements in autonomous driving and robot navigation, there is a growing demand for lifelong learning models capable of estimating metric (absolute) depth. Lifelong learning approaches potentially offer significant cost…

The perception of autonomous vehicles using radars has attracted increased research interest due its ability to operate in fog and bad weather. However, training radar models is hindered by the cost and difficulty of annotating large-scale…

Autonomous navigation has become an increasingly popular machine learning application. Recent advances in deep learning have also resulted in great improvements to autonomous navigation. However, prior outdoor autonomous navigation depends…

Self-supervised monocular depth estimation methods aim to be used in critical applications such as autonomous vehicles for environment analysis. To circumvent the potential imperfections of these approaches, a quantification of the…

The advent of deep learning has brought an impressive advance to monocular depth estimation, e.g., supervised monocular depth estimation has been thoroughly investigated. However, the large amount of the RGB-to-depth dataset may not be…

In contrast to extensive studies on general vision, pre-training for scalable visual autonomous driving remains seldom explored. Visual autonomous driving applications require features encompassing semantics, 3D geometry, and temporal…

Depth completion, the technique of estimating a dense depth image from sparse depth measurements, has a variety of applications in robotics and autonomous driving. However, depth completion faces 3 main challenges: the irregularly spaced…

In this paper, we investigate a predictive approach for collision risk assessment in autonomous and assisted driving. A deep predictive model is trained to anticipate imminent accidents from traditional video streams. In particular, the…

Self-supervised monocular depth estimation aims to infer depth information without relying on labeled data. However, the lack of labeled information poses a significant challenge to the model's representation, limiting its ability to…

We consider the problem of next frame prediction from video input. A recurrent convolutional neural network is trained to predict depth from monocular video input, which, along with the current video image and the camera trajectory, can…

Depth estimation aims to predict dense depth maps. In autonomous driving scenes, sparsity of annotations makes the task challenging. Supervised models produce concave objects due to insufficient structural information. They overfit to valid…

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 camera's aperture as supervision. Prior works use a depth sensor's outputs or images of the…

Navigating off-road with a fast autonomous vehicle depends on a robust perception system that differentiates traversable from non-traversable terrain. Typically, this depends on a semantic understanding which is based on supervised learning…