Related papers: Occlusion Guided Self-supervised Scene Flow Estima…

3D Multi-Object Tracking (MOT) is an important part of the unmanned vehicle perception module. Most methods optimize object detection and data association independently. These methods make the network structure complicated and limit the…

Monocular 3D lane detection is essential for autonomous driving, but challenging due to the inherent lack of explicit spatial information. Multi-modal approaches rely on expensive depth sensors, while methods incorporating fully-supervised…

In autonomous driving, accurately estimating the state of surrounding obstacles is critical for safe and robust path planning. However, this perception task is difficult, particularly for generic obstacles/objects, due to appearance and…

Given a single RGB image of a complex outdoor road scene in the perspective view, we address the novel problem of estimating an occlusion-reasoned semantic scene layout in the top-view. This challenging problem not only requires an accurate…

Autonomous driving is a safety-critical application, and it is therefore a top priority that the accompanying assistance systems are able to provide precise information about the surrounding environment of the vehicle. Tasks such as 3D…

Accurate perception of dynamic traffic scenes is crucial for high-level autonomous driving systems, requiring robust object motion estimation and instance segmentation. However, traditional methods often treat them as separate tasks,…

In this paper, we study the problem of jointly estimating the optical flow and scene flow from synchronized 2D and 3D data. Previous methods either employ a complex pipeline that splits the joint task into independent stages, or fuse 2D and…

A crucial task in scene understanding is 3D object detection, which aims to detect and localize the 3D bounding boxes of objects belonging to specific classes. Existing 3D object detectors heavily rely on annotated 3D bounding boxes during…

This article proposes a novel unsupervised learning framework for detecting the number of tunnel junctions in subterranean environments based on acquired 2D point clouds. The implementation of the framework provides valuable information for…

Estimating scene flow in RGB-D videos is attracting much interest of the computer vision researchers, due to its potential applications in robotics. The state-of-the-art techniques for scene flow estimation, typically rely on the knowledge…

Despite their irresistible success, deep learning algorithms still heavily rely on annotated data. On the other hand, unsupervised settings pose many challenges, especially about determining the right inductive bias in diverse scenarios.…

We address the problem of joint optical flow and camera motion estimation in rigid scenes by incorporating geometric constraints into an unsupervised deep learning framework. Unlike existing approaches which rely on brightness constancy and…

Point cloud data has been extensively studied due to its compact form and flexibility in representing complex 3D structures. The ability of point cloud data to accurately capture and represent intricate 3D geometry makes it an ideal choice…

Estimating geometric elements such as depth, camera motion, and optical flow from images is an important part of the robot's visual perception. We use a joint self-supervised method to estimate the three geometric elements. Depth network,…

Scene flow is a description of real world motion in 3D that contains more information than optical flow. Because of its complexity there exists no applicable variant for real-time scene flow estimation in an automotive or commercial vehicle…

Recent learning-based LiDAR odometry methods have demonstrated their competitiveness. However, most methods still face two substantial challenges: 1) the 2D projection representation of LiDAR data cannot effectively encode 3D structures…

We identify occlusion reasoning as a fundamental yet overlooked aspect for 3D layout-conditioned generation. It is essential for synthesizing partially occluded objects with depth-consistent geometry and scale. While existing methods can…

Manual annotation of large-scale point cloud dataset for varying tasks such as 3D object classification, segmentation and detection is often laborious owing to the irregular structure of point clouds. Self-supervised learning, which…

Although multi-scale concepts have recently proven useful for recurrent network architectures in the field of optical flow and stereo, they have not been considered for image-based scene flow so far. Hence, based on a single-scale recurrent…

We tackle the problem of estimating optical flow from a monocular camera in the context of autonomous driving. We build on the observation that the scene is typically composed of a static background, as well as a relatively small number of…