Related papers: Geometry-based Occlusion-Aware Unsupervised Stereo…

Unsupervised learning based depth estimation methods have received more and more attention as they do not need vast quantities of densely labeled data for training which are touch to acquire. In this paper, we propose a novel unsupervised…

With the advancement of vision-based autonomous driving technology, pedestrian detection have become an important component for improving traffic safety and driving system robustness. Nevertheless, in complex traffic scenarios, conventional…

In order to improve usability and safety, modern unmanned aerial vehicles (UAVs) are equipped with sensors to monitor the environment, such as laser-scanners and cameras. One important aspect in this monitoring process is to detect…

Recent advances in robot imitation learning have yielded powerful visuomotor policies capable of manipulating a wide variety of objects directly from monocular visual inputs. However, monocular observations inherently lack reliable depth…

Adjusting transparency is a common method of mitigating occlusion but is often detrimental for understanding the relative depth relationships between objects as well as removes potentially important information from the occluding object. We…

In this paper, we study the task of detecting semantic parts of an object, e.g., a wheel of a car, under partial occlusion. We propose that all models should be trained without seeing occlusions while being able to transfer the learned…

State-of-the-art approaches to infer dense depth measurements from images rely on CNNs trained end-to-end on a vast amount of data. However, these approaches suffer a drastic drop in accuracy when dealing with environments much different in…

In this paper we propose USegScene, a framework for semantically guided unsupervised learning of depth, optical flow and ego-motion estimation for stereo camera images using convolutional neural networks. Our framework leverages semantic…

Contrastive learning methods have significantly narrowed the gap between supervised and unsupervised learning on computer vision tasks. In this paper, we explore their application to geo-located datasets, e.g. remote sensing, where…

Understanding objects in terms of their individual parts is important, because it enables a precise understanding of the objects' geometrical structure, and enhances object recognition when the object is seen in a novel pose or under…

As an essential procedure in earth observation system, change detection (CD) aims to reveal the spatial-temporal evolution of the observation regions. A key prerequisite for existing change detection algorithms is aligned geo-references…

We propose the MAC-VO, a novel learning-based stereo VO that leverages the learned metrics-aware matching uncertainty for dual purposes: selecting keypoint and weighing the residual in pose graph optimization. Compared to traditional…

It has been recently shown that a convolutional neural network can learn optical flow estimation with unsupervised learning. However, the performance of the unsupervised methods still has a relatively large gap compared to its supervised…

Geometric alignment appears in a variety of applications, ranging from domain adaptation, optimal transport, and normalizing flows in machine learning; optical flow and learned augmentation in computer vision and deformable registration…

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…

Universal anomaly detection still remains a challenging problem in machine learning and medical image analysis. It is possible to learn an expected distribution from a single class of normative samples, e.g., through epistemic uncertainty…

Stereo depth estimation relies on optimal correspondence matching between pixels on epipolar lines in the left and right images to infer depth. In this work, we revisit the problem from a sequence-to-sequence correspondence perspective to…

Feature warping is a core technique in optical flow estimation; however, the ambiguity caused by occluded areas during warping is a major problem that remains unsolved. In this paper, we propose an asymmetric occlusion-aware feature…

We present a method for learning to drive on smooth terrain while simultaneously avoiding collisions in challenging off-road and unstructured outdoor environments using only visual inputs. Our approach applies a hybrid model-based and…

Hand-object pose estimation from monocular RGB images remains a significant challenge mainly due to the severe occlusions inherent in hand-object interactions. Existing methods do not sufficiently explore global structural perception and…