Related papers: VPIT: Real-time Embedded Single Object 3D Tracking…
Dynamic environments such as urban areas are still challenging for popular visual-inertial odometry (VIO) algorithms. Existing datasets typically fail to capture the dynamic nature of these environments, therefore making it difficult to…
3D object detectors for point clouds often rely on a pooling-based PointNet to encode sparse points into grid-like voxels or pillars. In this paper, we identify that the common PointNet design introduces an information bottleneck that…
Multi-object tracking (MOT) aims to associate target objects across video frames in order to obtain entire moving trajectories. With the advancement of deep neural networks and the increasing demand for intelligent video analysis, MOT has…
This paper proposes 3DGeoDet, a novel geometry-aware 3D object detection approach that effectively handles single- and multi-view RGB images in indoor and outdoor environments, showcasing its general-purpose applicability. The key challenge…
Vision-based roadside 3D object detection has attracted rising attention in autonomous driving domain, since it encompasses inherent advantages in reducing blind spots and expanding perception range. While previous work mainly focuses on…
In this paper we present a robust tracker to solve the multiple object tracking (MOT) problem, under the framework of tracking-by-detection. As the first contribution, we innovatively combine single object tracking (SOT) algorithms with…
Monocular 3D scene understanding tasks, such as object size estimation, heading angle estimation and 3D localization, is challenging. Successful modern day methods for 3D scene understanding require the use of a 3D sensor. On the other…
This work presents SGCDet, a novel multi-view indoor 3D object detection framework based on adaptive 3D volume construction. Unlike previous approaches that restrict the receptive field of voxels to fixed locations on images, we introduce a…
For robot manipulation, a complete and accurate object shape is desirable. Here, we present a method that combines visual and haptic reconstruction in a closed-loop pipeline. From an initial viewpoint, the object shape is reconstructed…
LiDAR point clouds can effectively depict the motion and posture of objects in three-dimensional space. Many studies accomplish the 3D object detection by voxelizing point clouds. However, in autonomous driving scenarios, the sparsity and…
Recent volumetric 3D reconstruction methods can produce very accurate results, with plausible geometry even for unobserved surfaces. However, they face an undesirable trade-off when it comes to multi-view fusion. They can fuse all available…
3D object detection is receiving increasing attention from both industry and academia thanks to its wide applications in various fields. In this paper, we propose Point-Voxel Region-based Convolution Neural Networks (PV-RCNNs) for 3D object…
Many LiDAR-based methods for detecting large objects, single-class object detection, or under easy situations were claimed to perform quite well. However, their performances of detecting small objects or under hard situations did not…
Recent advancements in technology have brought forth new forms of interactive applications, such as the social metaverse, where end users interact with each other through their virtual avatars. In such applications, precise full-body…
Inferring the stereo structure of objects in the real world is a challenging yet practical task. To equip deep models with this ability usually requires abundant 3D supervision which is hard to acquire. It is promising that we can simply…
3D object detection and dense depth estimation are one of the most vital tasks in autonomous driving. Multiple sensor modalities can jointly attribute towards better robot perception, and to that end, we introduce a method for jointly…
Modern multiple object tracking (MOT) systems usually follow the \emph{tracking-by-detection} paradigm. It has 1) a detection model for target localization and 2) an appearance embedding model for data association. Having the two models…
LiDAR-camera fusion can enhance the performance of 3D object detection by utilizing complementary information between depth-aware LiDAR points and semantically rich images. Existing voxel-based methods face significant challenges when…
Most learning-based methods estimate ego-motion by utilizing visual sensors, which suffer from dramatic lighting variations and textureless scenarios. In this paper, we incorporate sparse but accurate depth measurements obtained from lidars…
Recent work on 3D object detection advocates point cloud voxelization in birds-eye view, where objects preserve their physical dimensions and are naturally separable. When represented in this view, however, point clouds are sparse and have…