Related papers: Transformer-Based Model for Monocular Visual Odome…

This paper presents an approach that reconstructs a hand-held object from a monocular video. In contrast to many recent methods that directly predict object geometry by a trained network, the proposed approach does not require any learned…

Accurate state estimation for flexible robotic systems poses significant challenges, particularly for platforms with dynamically deforming structures that invalidate rigid-body assumptions. This paper addresses this problem and enables the…

Visual motion estimation is a well-studied challenge in autonomous navigation. Recent work has focused on addressing multimotion estimation in highly dynamic environments. These environments not only comprise multiple, complex motions but…

Recent visual odometry (VO) methods incorporating geometric algorithm into deep-learning architecture have shown outstanding performance on the challenging monocular VO task. Despite encouraging results are shown, previous methods ignore…

With the development of computer vision, visual odometry is adopted by more and more mobile robots. However, we found that not only its own pose, but the poses of other moving objects are also crucial for the decision of the robot. In…

This paper proposes a new lightweight Transformer-based lifter that maps short sequences of human 2D joint positions to 3D poses using a single camera. The proposed model takes as input geometric priors including segment lengths and camera…

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 transformers have recently emerged as an effective alternative to convolutional networks for action classification. However, most prior video transformers adopt either global space-time attention or hand-defined strategies to compare…

Monocular depth estimation has been actively studied in fields such as robot vision, autonomous driving, and 3D scene understanding. Given a sequence of color images, unsupervised learning methods based on the framework of…

We present a novel method for simultaneous learning of depth, egomotion, object motion, and camera intrinsics from monocular videos, using only consistency across neighboring video frames as supervision signal. Similarly to prior work, our…

Recently, deep-learning-based approaches have been widely studied for deformable image registration task. However, most efforts directly map the composite image representation to spatial transformation through the convolutional neural…

This paper proposes a method to estimate the pose of a sensor mounted on a vehicle as the vehicle moves through the world, an important topic for autonomous driving systems. Based on a set of commonly deployed vehicular odometric sensors,…

This paper aims to address the problem of supervised monocular depth estimation. We start with a meticulous pilot study to demonstrate that the long-range correlation is essential for accurate depth estimation. Therefore, we propose to…

We propose a novel end-to-end method for cross-view pose estimation. Given a ground-level query image and an aerial image that covers the query's local neighborhood, the 3 Degrees-of-Freedom camera pose of the query is estimated by matching…

Moving object Detection (MOD) is a critical task in autonomous driving as moving agents around the ego-vehicle need to be accurately detected for safe trajectory planning. It also enables appearance agnostic detection of objects based on…

Self-supervised monocular depth estimation has emerged as a promising approach since it does not rely on labeled training data. Most methods combine convolution and Transformer to model long-distance dependencies to estimate depth…

Video understanding tasks have traditionally been modeled by two separate architectures, specially tailored for two distinct tasks. Sequence-based video tasks, such as action recognition, use a video backbone to directly extract…

Vision transformers have recently emerged as an effective alternative to convolutional networks for action recognition. However, vision transformers still struggle with geometric variations prevalent in video data. This paper proposes a…

Most previous learning-based visual odometry (VO) methods take VO as a pure tracking problem. In contrast, we present a VO framework by incorporating two additional components called Memory and Refining. The Memory component preserves…

Visual segmentation seeks to partition images, video frames, or point clouds into multiple segments or groups. This technique has numerous real-world applications, such as autonomous driving, image editing, robot sensing, and medical…