Related papers: PDM-SSD: Single-Stage Three-Dimensional Object Det…
Fully-supervised category-level pose estimation aims to determine the 6-DoF poses of unseen instances from known categories, requiring expensive mannual labeling costs. Recently, various self-supervised category-level pose estimation…
We present an improved approach for 3D object detection in point cloud data based on the Frustum PointNet (F-PointNet). Compared to the original F-PointNet, our newly proposed method considers the point neighborhood when computing point…
Point cloud sequences are commonly used to accurately detect 3D objects in applications such as autonomous driving. Current top-performing multi-frame detectors mostly follow a Detect-and-Fuse framework, which extracts features from each…
Learning and analyzing 3D point clouds with deep networks is challenging due to the sparseness and irregularity of the data. In this paper, we present a data-driven point cloud upsampling technique. The key idea is to learn multi-level…
Current zero-shot Camouflaged Object Segmentation methods typically employ a two-stage pipeline (discover-then-segment): using MLLMs to obtain visual prompts, followed by SAM segmentation. However, relying solely on MLLMs for camouflaged…
Small object detection for 3D point cloud is a challenging problem because of two limitations: (1) Perceiving small objects is much more diffcult than normal objects due to the lack of valid points. (2) Small objects are easily blocked…
In this paper, we propose an end-to-end deep learning network named 3dDepthNet, which produces an accurate dense depth image from a single pair of sparse LiDAR depth and color image for robotics and autonomous driving tasks. Based on the…
Current methods for dense 3D point tracking in dynamic scenes typically rely on pairwise processing, require known camera poses, or assume temporal ordering of input frames, thereby constraining their flexibility and applicability.…
Effective point cloud processing is crucial to LiDARbased autonomous driving systems. The capability to understand features at multiple scales is required for object detection of intelligent vehicles, where road users may appear in…
3D point cloud semantic segmentation aims to group all points into different semantic categories, which benefits important applications such as point cloud scene reconstruction and understanding. Existing supervised point cloud semantic…
Recent camera-based 3D object detection methods have introduced sequential frames to improve the detection performance hoping that multiple frames would mitigate the large depth estimation error. Despite improved detection performance,…
We present SKD, a novel keypoint detector that uses saliency to determine the best candidates from a point cloud for tasks such as registration and reconstruction. The approach can be applied to any differentiable deep learning descriptor…
Spiking Neural Networks (SNNs) provide an energy-efficient way to extract 3D spatio-temporal features. Point clouds are sparse 3D spatial data, which suggests that SNNs should be well-suited for processing them. However, when applying SNNs…
Despite substantial progress in 3D object detection, advanced 3D detectors often suffer from heavy computation overheads. To this end, we explore the potential of knowledge distillation (KD) for developing efficient 3D object detectors,…
Wide-range and fine-grained vehicle detection plays a critical role in enabling active safety features in intelligent driving systems. However, existing vehicle detection methods based on rectangular bounding boxes (BBox) often struggle…
Producing traversability maps and understanding the surroundings are crucial prerequisites for autonomous navigation. In this paper, we address the problem of traversability assessment using point clouds. We propose a novel pillar feature…
3D object detection often involves complicated training and testing pipelines, which require substantial domain knowledge about individual datasets. Inspired by recent non-maximum suppression-free 2D object detection models, we propose a 3D…
For most of the object detectors based on multi-scale feature maps, the shallow layers are rich in fine spatial information and thus mainly responsible for small object detection. The performance of small object detection, however, is still…
Monocular image-based 3D perception has become an active research area in recent years owing to its applications in autonomous driving. Approaches to monocular 3D perception including detection and tracking, however, often yield inferior…
Based on point spread function (PSF) engineering and astigmatism due to a pair of cylindrical lenses, a novel compressed imaging mechanism is proposed to achieve single-shot incoherent 3D imaging. The speckle-like PSF of the imaging system…