Related papers: D3S -- A Discriminative Single Shot Segmentation T…
Most of 3D single object trackers (SOT) in point clouds follow the two-stream multi-stage 3D Siamese or motion tracking paradigms, which process the template and search area point clouds with two parallel branches, built on supervised point…
In the same vein of discriminative one-shot learning, Siamese networks allow recognizing an object from a single exemplar with the same class label. However, they do not take advantage of the underlying structure of the data and the…
Generic object tracking remains an important yet challenging task in computer vision due to complex spatio-temporal dynamics, especially in the presence of occlusions, similar distractors, and appearance variations. Over the past two…
As a milestone for video object segmentation, one-shot video object segmentation (OSVOS) has achieved a large margin compared to the conventional optical-flow based methods regarding to the segmentation accuracy. Its excellent performance…
The objective of this paper is self-supervised representation learning, with the goal of solving semi-supervised video object segmentation (a.k.a. dense tracking). We make the following contributions: (i) we propose to improve the existing…
The tracking algorithm performance depends on video content. This paper presents a new multi-object tracking approach which is able to cope with video content variations. First the object detection is improved using Kanade- Lucas-Tomasi…
Indoor traversability segmentation aims to identify safe, navigable free space for autonomous agents, which is critical for robotic navigation. Pure vision-based models often fail to detect thin obstacles, such as chair legs, which can pose…
We present DroTrack, a high-speed visual single-object tracking framework for drone-captured video sequences. Most of the existing object tracking methods are designed to tackle well-known challenges, such as occlusion and cluttered…
Counting and tracking dense crowds in large-scale scenes is a highly practical yet challenging problem. Existing methods mostly rely on fixed-camera datasets with limited scene coverage, making them inadequate for crowd analysis in…
One object class may show large variations due to diverse illuminations, backgrounds and camera viewpoints. Traditional object detection methods often perform worse under unconstrained video environments. To address this problem, many…
Direct methods have shown excellent performance in the applications of visual odometry and SLAM. In this work we propose to leverage their effectiveness for the task of 3D multi-object tracking. To this end, we propose DirectTracker, a…
3D Multi-Object Tracking (MOT) obtains significant performance improvements with the rapid advancements in 3D object detection, particularly in cost-effective multi-camera setups. However, the prevalent end-to-end training approach for…
Visual tracking fundamentally involves regressing the state of the target in each frame of a video. Despite significant progress, existing regression-based trackers still tend to experience failures and inaccuracies. To enhance the…
Recently, transformer-based methods have shown exceptional performance in monocular 3D object detection, which can predict 3D attributes from a single 2D image. These methods typically use visual and depth representations to generate query…
This report presents a framework called Segment And Track Anything (SAMTrack) that allows users to precisely and effectively segment and track any object in a video. Additionally, SAM-Track employs multimodal interaction methods that enable…
The ability to detect and segment moving objects in a scene is essential for building consistent maps, making future state predictions, avoiding collisions, and planning. In this paper, we address the problem of moving object segmentation…
State-of-the-art visual localization methods mostly rely on complex procedures to match local descriptors and 3D point clouds. However, these procedures can incur significant costs in terms of inference, storage, and updates over time. In…
Feature tracking is the building block of many applications such as visual odometry, augmented reality, and target tracking. Unfortunately, the state-of-the-art vision-based tracking algorithms fail in surgical images due to the challenges…
Siamese network has been a de facto benchmark framework for 3D LiDAR object tracking with a shared-parametric encoder extracting features from template and search region, respectively. This paradigm relies heavily on an additional matching…
Recently, neural architecture search (NAS) has been applied to automatically search high-performance networks for medical image segmentation. The NAS search space usually contains a network topology level (controlling connections among…