Related papers: OmniMVS: End-to-End Learning for Omnidirectional S…
Omnidirectional video is an essential component of Virtual Reality. Although various methods have been proposed to generate content that can be viewed with six degrees of freedom (6-DoF), existing systems usually involve complex depth…
Despite learning based methods showing promising results in single view depth estimation and visual odometry, most existing approaches treat the tasks in a supervised manner. Recent approaches to single view depth estimation explore the…
In the last decade, numerous supervised deep learning approaches requiring large amounts of labeled data have been proposed for visual-inertial odometry (VIO) and depth map estimation. To overcome the data limitation, self-supervised…
Depth estimation is a cornerstone of a vast number of applications requiring 3D assessment of the environment, such as robotics, augmented reality, and autonomous driving to name a few. One prominent technique for depth estimation is stereo…
We propose Stereo Direct Sparse Odometry (Stereo DSO) as a novel method for highly accurate real-time visual odometry estimation of large-scale environments from stereo cameras. It jointly optimizes for all the model parameters within the…
Multi-Camera arrays are increasingly employed in both consumer and industrial applications, and various passive techniques are documented to estimate depth from such camera arrays. Current depth estimation methods provide useful estimations…
Head-mounted 360{\deg} displays and portable 360{\deg} cameras have significantly progressed, providing viewers a realistic and immersive experience. However, many omnidirectional videos have low frame rates that can lead to visual fatigue,…
Visibility underwater is challenging, and degrades as the distance between the subject and camera increases, making vision tasks in the forward-looking direction more difficult. We have collected underwater forward-looking stereo-vision and…
360{\deg} images can provide an omnidirectional field of view which is important for stable and long-term scene perception. In this paper, we explore 360{\deg} images for visual object tracking and perceive new challenges caused by large…
The success of monocular depth estimation relies on large and diverse training sets. Due to the challenges associated with acquiring dense ground-truth depth across different environments at scale, a number of datasets with distinct…
As virtual reality gains popularity, the demand for controllable creation of immersive and dynamic omnidirectional videos (ODVs) is increasing. While previous text-to-ODV generation methods achieve impressive results, they struggle with…
Single-view depth prediction is a fundamental problem in computer vision. Recently, deep learning methods have led to significant progress, but such methods are limited by the available training data. Current datasets based on 3D sensors…
Learning depth and optical flow via deep neural networks by watching videos has made significant progress recently. In this paper, we jointly solve the two tasks by exploiting the underlying geometric rules within stereo videos.…
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…
Depth estimation is a critical technology in autonomous driving, and multi-camera systems are often used to achieve a 360$^\circ$ perception. These 360$^\circ$ camera sets often have limited or low-quality overlap regions, making multi-view…
We study how autonomous robots can learn by themselves to improve their depth estimation capability. In particular, we investigate a self-supervised learning setup in which stereo vision depth estimates serve as targets for a convolutional…
Depth estimation from a single image represents a fascinating, yet challenging problem with countless applications. Recent works proved that this task could be learned without direct supervision from ground truth labels leveraging image…
Supervised learning with deep convolutional neural networks (DCNNs) has seen huge adoption in stereo matching. However, the acquisition of large-scale datasets with well-labeled ground truth is cumbersome and labor-intensive, making…
We propose a novel monocular visual odometry (VO) system called UnDeepVO in this paper. UnDeepVO is able to estimate the 6-DoF pose of a monocular camera and the depth of its view by using deep neural networks. There are two salient…
We introduce Point-MVSNet, a novel point-based deep framework for multi-view stereo (MVS). Distinct from existing cost volume approaches, our method directly processes the target scene as point clouds. More specifically, our method predicts…