Related papers: Beyond Tracking: Selecting Memory and Refining Pos…
End-to-end reinforcement learning on images showed significant progress in the recent years. Data-based approach leverage data augmentation and domain randomization while representation learning methods use auxiliary losses to learn…
Generally, high-level features provide more geometrical information compared to point features, which can be exploited to further constrain motions. Planes are commonplace in man-made environments, offering an active means to reduce drift,…
Combining cameras and inertial measurement units (IMUs) has been proven effective in motion tracking, as these two sensing modalities offer complementary characteristics that are suitable for fusion. While most works focus on global-shutter…
Deep learning algorithms have driven expressive progress in many complex tasks. The loss function is a core component of deep learning techniques, guiding the learning process of neural networks. This paper contributes by introducing a…
Video Object Segmentation (VOS) is foundational to numerous computer vision applications, including surveillance, autonomous driving, robotics and generative video editing. However, existing VOS models often struggle with precise mask…
Data-driven visual odometry (VO) is a critical subroutine for autonomous edge robotics, and recent progress in the field has produced highly accurate point predictions in complex environments. However, emerging autonomous edge robotics…
Depth and ego-motion estimations are essential for the localization and navigation of autonomous robots and autonomous driving. Recent studies make it possible to learn the per-pixel depth and ego-motion from the unlabeled monocular video.…
Neglecting the effects of rolling-shutter cameras for visual odometry (VO) severely degrades accuracy and robustness. In this paper, we propose a novel direct monocular VO method that incorporates a rolling-shutter model. Our approach…
Estimating motion from images is a well-studied problem in computer vision and robotics. Previous work has developed techniques to estimate the motion of a moving camera in a largely static environment (e.g., visual odometry) and to segment…
Underwater visual localization remains challenging due to wavelength-dependent attenuation, poor texture, and non-Gaussian sensor noise. We introduce MARVO, a physics-aware, learning-integrated odometry framework that fuses underwater image…
Referring Video Object Segmentation (R-VOS) methods face challenges in maintaining consistent object segmentation due to temporal context variability and the presence of other visually similar objects. We propose an end-to-end R-VOS…
In the field of Simultaneous Localization and Mapping (SLAM), researchers have always pursued better performance in terms of accuracy and time cost. Traditional algorithms typically rely on fundamental geometric elements in images to…
In this paper we propose a framework for integrating map-based relocalization into online direct visual odometry. To achieve map-based relocalization for direct methods, we integrate image features into Direct Sparse Odometry (DSO) and rely…
This paper presents a visual-inertial odometry (VIO) method using long-tracked features. Long-tracked features can constrain more visual frames, reducing localization drift. However, they may also lead to accumulated matching errors and…
The RGB-Depth (RGB-D) Video Object Segmentation (VOS) aims to integrate the fine-grained texture information of RGB with the spatial geometric clues of depth modality, boosting the performance of segmentation. However, off-the-shelf RGB-D…
Recent decades have witnessed a significant increase in the use of visual odometry(VO) in the computer vision area. It has also been used in varieties of robotic applications, for example on the Mars Exploration Rovers. This paper, firstly,…
Multimodal vision-language (VL) learning has noticeably pushed the tendency toward generic intelligence owing to emerging large foundation models. However, tracking, as a fundamental vision problem, surprisingly enjoys less bonus from…
Existing visual object tracking usually learns a bounding-box based template to match the targets across frames, which cannot accurately learn a pixel-wise representation, thereby being limited in handling severe appearance variations. To…
Deep learning based visual trackers entail offline pre-training on large volumes of video datasets with accurate bounding box annotations that are labor-expensive to achieve. We present a new framework to facilitate bounding box annotations…
Template-matching methods for visual tracking have gained popularity recently due to their good performance and fast speed. However, they lack effective ways to adapt to changes in the target object's appearance, making their tracking…