Related papers: Sequential Adversarial Learning for Self-Supervise…

The emergence of visual foundation models has revolutionized visual odometry~(VO) and SLAM, enabling pose estimation and dense reconstruction within a single feed-forward network. However, unlike traditional pipelines that leverage keyframe…

Visual odometry networks commonly use pretrained optical flow networks in order to derive the ego-motion between consecutive frames. The features extracted by these networks represent the motion of all the pixels between frames. However,…

Recently end-to-end unsupervised deep learning methods have achieved an effect beyond geometric methods for visual depth and ego-motion estimation tasks. These data-based learning methods perform more robustly and accurately in some of the…

Visual odometry (VO) is essential for enabling accurate point-goal navigation of embodied agents in indoor environments where GPS and compass sensors are unreliable and inaccurate. However, traditional VO methods face challenges in…

We present a self-supervised learning algorithm for 3D human pose estimation of a single person based on a multiple-view camera system and 2D body pose estimates for each view. To train our model, represented by a deep neural network, we…

Using generative models for Inverse Graphics is an active area of research. However, most works focus on developing models for supervised and semi-supervised methods. In this paper, we study the problem of unsupervised learning of 3D…

While recent deep monocular depth estimation approaches based on supervised regression have achieved remarkable performance, costly ground truth annotations are required during training. To cope with this issue, in this paper we present a…

Although a wide variety of deep neural networks for robust Visual Odometry (VO) can be found in the literature, they are still unable to solve the drift problem in long-term robot navigation. Thus, this paper aims to propose novel deep…

Learning visual semantic similarity is a critical challenge in bridging the gap between images and texts. However, there exist inherent variations between vision and language data, such as information density, i.e., images can contain…

Learning-based monocular visual odometry (VO) poses robustness, generalization, and efficiency challenges in robotics. Recent advances in visual foundation models, such as DINOv2, have improved robustness and generalization in various…

In this study, we address the critical challenge of balancing speed and accuracy while maintaining interpretablity in visual odometry (VO) systems, a pivotal aspect in the field of autonomous navigation and robotics. Traditional VO systems…

Visual odometry is a fundamental task for many applications on mobile devices and robotic platforms. Since such applications are oftentimes not limited to predefined target domains and learning-based vision systems are known to generalize…

Deep learning approaches for Visual-Inertial Odometry (VIO) have proven successful, but they rarely focus on incorporating robust fusion strategies for dealing with imperfect input sensory data. We propose a novel end-to-end selective…

Recent progress in contrastive learning has revolutionized unsupervised representation learning. Concretely, multiple views (augmentations) from the same image are encouraged to map to the similar embeddings, while views from different…

In this paper, we present a multi-camera visual odometry (VO) system for an autonomous vehicle. Our system mainly consists of a virtual LiDAR and a pose tracker. We use a perspective transformation method to synthesize a surround-view image…

The promise of self-supervised learning (SSL) is to leverage large amounts of unlabeled data to solve complex tasks. While there has been excellent progress with simple, image-level learning, recent methods have shown the advantage of…

Most geometric approaches to monocular Visual Odometry (VO) provide robust pose estimates, but sparse or semi-dense depth estimates. Off late, deep methods have shown good performance in generating dense depths and VO from monocular images…

Landmark/pose estimation in single monocular images have received much effort in computer vision due to its important applications. It remains a challenging task when input images severe occlusions caused by, e.g., adverse camera views.…

Recently, a multitude of methods for image-to-image translation have demonstrated impressive results on problems such as multi-domain or multi-attribute transfer. The vast majority of such works leverages the strengths of adversarial…

Event-based cameras are bio-inspired vision sensors whose pixels work independently from each other and respond asynchronously to brightness changes, with microsecond resolution. Their advantages make it possible to tackle challenging…