Related papers: Unsupervised Deep Persistent Monocular Visual Odom…
Hybrid pipelines that combine deep learning with classical optimization have established themselves as the dominant approach to visual odometry (VO). By integrating neural network predictions with bundle adjustment, these models estimate…
Dynamic scenes that contain both object motion and egomotion are a challenge for monocular visual odometry (VO). Another issue with monocular VO is the scale ambiguity, i.e. these methods cannot estimate scene depth and camera motion in…
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 technology for Visual Odometry (VO) that estimates the position and orientation of the moving object through analyzing the image sequences captured by on-board cameras, has been well investigated with the rising interest in autonomous…
We present a novel real-time visual odometry framework for a stereo setup of a depth and high-resolution event camera. Our framework balances accuracy and robustness against computational efficiency towards strong performance in challenging…
Conventional self-supervised monocular depth prediction methods are based on a static environment assumption, which leads to accuracy degradation in dynamic scenes due to the mismatch and occlusion problems introduced by object motions.…
Depth estimation is critical for any robotic system. In the past years estimation of depth from monocular images have shown great improvement, however, in the underwater environment results are still lagging behind due to appearance changes…
Recent advances in self-supervised learning havedemonstrated that it is possible to learn accurate monoculardepth reconstruction from raw video data, without using any 3Dground truth for supervision. However, in robotics…
Depth Estimation has wide reaching applications in the field of Computer vision such as target tracking, augmented reality, and self-driving cars. The goal of Monocular Depth Estimation is to predict the depth map, given a 2D monocular RGB…
Accurate and efficient dense metric depth estimation is crucial for 3D visual perception in robotics and XR. In this paper, we develop a monocular visual-inertial motion and depth (VIMD) learning framework to estimate dense metric depth by…
One of the main open challenges in visual odometry (VO) is the robustness to difficult illumination conditions or high dynamic range (HDR) environments. The main difficulties in these situations come from both the limitations of the sensors…
Monocular visual-inertial odometry (VIO) is a critical problem in robotics and autonomous driving. Traditional methods solve this problem based on filtering or optimization. While being fully interpretable, they rely on manual interference…
Effectively localizing an agent in a realistic, noisy setting is crucial for many embodied vision tasks. Visual Odometry (VO) is a practical substitute for unreliable GPS and compass sensors, especially in indoor environments. While…
We present a self-supervised learning framework to estimate the individual object motion and monocular depth from video. We model the object motion as a 6 degree-of-freedom rigid-body transformation. The instance segmentation mask is…
The advancement of visual tracking has continuously been brought by deep learning models. Typically, supervised learning is employed to train these models with expensive labeled data. In order to reduce the workload of manual annotations…
Recently unsupervised learning of depth from videos has made remarkable progress and the results are comparable to fully supervised methods in outdoor scenes like KITTI. However, there still exist great challenges when directly applying…
We propose a novel deep visual odometry (VO) method that considers global information by selecting memory and refining poses. Existing learning-based methods take the VO task as a pure tracking problem via recovering camera poses from image…
In this paper, we delve into semi-supervised object detection where unlabeled images are leveraged to break through the upper bound of fully-supervised object detection models. Previous semi-supervised methods based on pseudo labels are…
This paper proposes a novel approach to stereo visual odometry without stereo matching. It is particularly robust in scenes of repetitive high-frequency textures. Referred to as DSVO (Direct Stereo Visual Odometry), it operates directly on…
Recent supervised multi-view depth estimation networks have achieved promising results. Similar to all supervised approaches, these networks require ground-truth data during training. However, collecting a large amount of multi-view depth…