相关论文: 3D Spatial Recognition without Spatially Labeled 3…

Competitive point cloud semantic segmentation results usually rely on a large amount of labeled data. However, data annotation is a time-consuming and labor-intensive task, particularly for three-dimensional point cloud data. Thus,…

Learning from bounding-boxes annotations has shown great potential in weakly-supervised 3D point cloud instance segmentation. However, we observed that existing methods would suffer severe performance degradation with perturbed bounding box…

Semantic segmentation of point cloud usually relies on dense annotation that is exhausting and costly, so it attracts wide attention to investigate solutions for the weakly supervised scheme with only sparse points annotated. Existing works…

Object discovery is a core task in computer vision. While fast progresses have been made in supervised object detection, its unsupervised counterpart remains largely unexplored. With the growth of data volume, the expensive cost of…

Object detection in 3D point clouds is a crucial task in a range of computer vision applications including robotics, autonomous cars, and augmented reality. This work addresses the object detection task in 3D point clouds using a highly…

3D object detection is essential for autonomous driving and robotic perception, yet its reliance on large-scale manually annotated data limits scalability and adaptability. To reduce annotation dependency, unsupervised and…

Supervised object detection and semantic segmentation require object or even pixel level annotations. When there exist image level labels only, it is challenging for weakly supervised algorithms to achieve accurate predictions. The accuracy…

Point cloud registration is the process of aligning a pair of point sets via searching for a geometric transformation. Recent works leverage the power of deep learning for registering a pair of point sets. However, unfortunately, deep…

Reducing the quantity of annotations required for supervised training is vital when labels are scarce and costly. This reduction is particularly important for semantic segmentation tasks involving 3D datasets, which are often significantly…

Point clouds provide a flexible and natural representation usable in countless applications such as robotics or self-driving cars. Recently, deep neural networks operating on raw point cloud data have shown promising results on supervised…

Object localization is an important computer vision problem with a variety of applications. The lack of large scale object-level annotations and the relative abundance of image-level labels makes a compelling case for weak supervision in…

Pixel-wise clean annotation is necessary for fully-supervised semantic segmentation, which is laborious and expensive to obtain. In this paper, we propose a weakly supervised 2D semantic segmentation model by incorporating sparse bounding…

Label-efficient LiDAR-based 3D object detection is currently dominated by weakly/semi-supervised methods. Instead of exclusively following one of them, we propose MixSup, a more practical paradigm simultaneously utilizing massive cheap…

We propose a weakly-supervised multi-view learning approach to learn category-specific surface mapping without dense annotations. We learn the underlying surface geometry of common categories, such as human faces, cars, and airplanes, given…

Deep neural network models have achieved remarkable progress in 3D scene understanding while trained in the closed-set setting and with full labels. However, the major bottleneck is that these models do not have the capacity to recognize…

Despite the importance of unsupervised object detection, to the best of our knowledge, there is no previous work addressing this problem. One main issue, widely known to the community, is that object boundaries derived only from 2D image…

We propose a weakly supervised semantic segmentation method for point clouds that predicts "per-point" labels from just "whole-scene" annotations. The key challenge here is the discrepancy between the target of dense per-point semantic…

Cross-category anomaly detection for 3D point clouds aims to determine whether an unseen object belongs to a target category using only a few normal examples. Most existing methods rely on category-specific training, which limits their…

3D object detection is an important task in computer vision. Most existing methods require a large number of high-quality 3D annotations, which are expensive to collect. Especially for outdoor scenes, the problem becomes more severe due to…

Real-time 3D object detection from point clouds is essential for dynamic scene understanding in applications such as augmented reality, robotics and navigation. We introduce a novel Spatial-prioritized and Rank-aware 3D object detection…