English
Related papers

Related papers: Box2Seg: Learning Semantics of 3D Point Clouds wit…

200 papers

Existing weakly or semi-supervised semantic segmentation methods utilize image or box-level supervision to generate pseudo-labels for weakly labeled images. However, due to the lack of strong supervision, the generated pseudo-labels are…

Computer Vision and Pattern Recognition · Computer Science 2021-10-22 Md Amirul Islam , Matthew Kowal , Sen Jia , Konstantinos G. Derpanis , Neil D. B. Bruce

We develop a novel learning scheme named Self-Prediction for 3D instance and semantic segmentation of point clouds. Distinct from most existing methods that focus on designing convolutional operators, our method designs a new learning…

Computer Vision and Pattern Recognition · Computer Science 2020-07-28 Jinxian Liu , Minghui Yu , Bingbing Ni , Ye Chen

Point cloud analysis has a wide range of applications in many areas such as computer vision, robotic manipulation, and autonomous driving. While deep learning has achieved remarkable success on image-based tasks, there are many unique…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Sushmita Sarker , Prithul Sarker , Gunner Stone , Ryan Gorman , Alireza Tavakkoli , George Bebis , Javad Sattarvand

Deep learning models are the state-of-the-art methods for semantic point cloud segmentation, the success of which relies on the availability of large-scale annotated datasets. However, it can be extremely time-consuming and prohibitively…

Computer Vision and Pattern Recognition · Computer Science 2021-04-13 Xian Shi , Xun Xu , Ke Chen , Lile Cai , Chuan Sheng Foo , Kui Jia

We propose a novel, conceptually simple and general framework for instance segmentation on 3D point clouds. Our method, called 3D-BoNet, follows the simple design philosophy of per-point multilayer perceptrons (MLPs). The framework directly…

Computer Vision and Pattern Recognition · Computer Science 2019-09-06 Bo Yang , Jianan Wang , Ronald Clark , Qingyong Hu , Sen Wang , Andrew Markham , Niki Trigoni

We study the problem of unsupervised 3D semantic segmentation on raw point clouds without needing human labels in training. Existing methods usually formulate this problem into learning per-point local features followed by a simple grouping…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Zihui Zhang , Weisheng Dai , Hongtao Wen , Bo Yang

Semantic segmentation of 3D point cloud data often comes with high annotation costs. Active learning automates the process of selecting which data to annotate, reducing the total amount of annotation needed to achieve satisfactory…

Computer Vision and Pattern Recognition · Computer Science 2025-12-08 Johannes Meyer , Jasper Hoffmann , Felix Schulz , Dominik Merkle , Daniel Buescher , Alexander Reiterer , Joschka Boedecker , Wolfram Burgard

Semantic segmentation is an important and well-known task in the field of computer vision, in which we attempt to assign a corresponding semantic class to each input element. When it comes to semantic segmentation of 2D images, the input…

Computer Vision and Pattern Recognition · Computer Science 2023-05-02 Ivan Martinović

Current state-of-the-art point cloud-based perception methods usually rely on large-scale labeled data, which requires expensive manual annotations. A natural option is to explore the unsupervised methodology for 3D perception tasks.…

Computer Vision and Pattern Recognition · Computer Science 2023-10-17 Jingyu Zhang , Huitong Yang , Dai-Jie Wu , Jacky Keung , Xuesong Li , Xinge Zhu , Yuexin Ma

Recently, several weakly supervised learning methods have been devoted to utilize bounding box supervision for training deep semantic segmentation models. Most existing methods usually leverage the generic proposal generators (e.g., dense…

Computer Vision and Pattern Recognition · Computer Science 2022-03-03 Chaohao Xie , Dongwei Ren , Lei Wang , Wangmeng Zuo

Recently, the self-supervised learning framework data2vec has shown inspiring performance for various modalities using a masked student-teacher approach. However, it remains open whether such a framework generalizes to the unique challenges…

Computer Vision and Pattern Recognition · Computer Science 2026-01-23 Karim Knaebel , Jonas Schult , Alexander Hermans , Bastian Leibe

Point cloud instance segmentation has achieved huge progress with the emergence of deep learning. However, these methods are usually data-hungry with expensive and time-consuming dense point cloud annotations. To alleviate the annotation…

Computer Vision and Pattern Recognition · Computer Science 2022-08-18 Yongbin Liao , Hongyuan Zhu , Yanggang Zhang , Chuangguan Ye , Tao Chen , Jiayuan Fan

In this paper, we propose PASS3D to achieve point-wise semantic segmentation for 3D point cloud. Our framework combines the efficiency of traditional geometric methods with robustness of deep learning methods, consisting of two stages: At…

Computer Vision and Pattern Recognition · Computer Science 2020-08-27 Xin Kong , Guangyao Zhai , Baoquan Zhong , Yong Liu

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…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Qingtao Yu , Heming Du , Chen Liu , Xin Yu

Classification and segmentation of 3D point clouds are important tasks in computer vision. Because of the irregular nature of point clouds, most of the existing methods convert point clouds into regular 3D voxel grids before they are used…

Computer Vision and Pattern Recognition · Computer Science 2018-12-05 Wei Zeng , Theo Gevers

Deep learning has achieved impressive results in nuclei segmentation, but the massive requirement for pixel-wise labels remains a significant challenge. To alleviate the annotation burden, existing methods generate pseudo masks for model…

Computer Vision and Pattern Recognition · Computer Science 2024-06-25 Ziyue Wang , Ye Zhang , Yifeng Wang , Linghan Cai , Yongbing Zhang

3D instance segmentation is crucial for understanding complex 3D environments, yet fully supervised methods require dense point-level annotations, resulting in substantial annotation costs and labor overhead. To mitigate this, box-level…

Computer Vision and Pattern Recognition · Computer Science 2025-10-15 Youngju Yoo , Seho Kim , Changick Kim

In this work, we propose to learn local descriptors for point clouds in a self-supervised manner. In each iteration of the training, the input of the network is merely one unlabeled point cloud. On top of our previous work, that directly…

Robotics · Computer Science 2020-03-12 Yijun Yuan , Jiawei Hou , Andreas Nüchter , Sören Schwertfeger

3D instance segmentation methods often require fully-annotated dense labels for training, which are costly to obtain. In this paper, we present ClickSeg, a novel click-level weakly supervised 3D instance segmentation method that requires…

Computer Vision and Pattern Recognition · Computer Science 2023-07-20 Leyao Liu , Tao Kong , Minzhao Zhu , Jiashuo Fan , Lu Fang

Dominated point cloud-based 3D object detectors in autonomous driving scenarios rely heavily on the huge amount of accurately labeled samples, however, 3D annotation in the point cloud is extremely tedious, expensive and time-consuming. To…

Computer Vision and Pattern Recognition · Computer Science 2022-07-27 Junbo Yin , Jin Fang , Dingfu Zhou , Liangjun Zhang , Cheng-Zhong Xu , Jianbing Shen , Wenguan Wang