English
Related papers

Related papers: Joint Supervised and Self-Supervised Learning for …

200 papers

Existing deep learning algorithms for point cloud analysis mainly concern discovering semantic patterns from global configuration of local geometries in a supervised learning manner. However, very few explore geometric properties revealing…

Computer Vision and Pattern Recognition · Computer Science 2020-09-18 Lulu Tang , Ke Chen , Chaozheng Wu , Yu Hong , Kui Jia , Zhixin Yang

Semantic understanding of 3D point clouds is important for various robotics applications. Given that point-wise semantic annotation is expensive, in this paper, we address the challenge of learning models with extremely sparse labels. The…

Computer Vision and Pattern Recognition · Computer Science 2021-09-20 Liyi Luo , Beiwen Tian , Hao Zhao , Guyue Zhou

With the rapid advancement of technology, 3D data acquisition and utilization have become increasingly prevalent across various fields, including computer vision, robotics, and geospatial analysis. 3D data, captured through methods such as…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Siming Yan

We introduce an unsupervised multi-task model to jointly learn point and shape features on point clouds. We define three unsupervised tasks including clustering, reconstruction, and self-supervised classification to train a multi-scale…

Computer Vision and Pattern Recognition · Computer Science 2019-10-21 Kaveh Hassani , Mike Haley

We propose a new supervized learning framework for oversegmenting 3D point clouds into superpoints. We cast this problem as learning deep embeddings of the local geometry and radiometry of 3D points, such that the border of objects presents…

Computer Vision and Pattern Recognition · Computer Science 2019-04-04 Loic Landrieu , Mohamed Boussaha

Rapid progress in 3D semantic segmentation is inseparable from the advances of deep network models, which highly rely on large-scale annotated data for training. To address the high cost and challenges of 3D point-level labeling, we present…

Computer Vision and Pattern Recognition · Computer Science 2021-10-18 Li Jiang , Shaoshuai Shi , Zhuotao Tian , Xin Lai , Shu Liu , Chi-Wing Fu , Jiaya Jia

Self-supervised learning on point clouds has gained a lot of attention recently, since it addresses the label-efficiency and domain-gap problems on point cloud tasks. In this paper, we propose a novel self-supervised framework to learn…

Computer Vision and Pattern Recognition · Computer Science 2022-01-11 Meng-Shiun Tsai , Pei-Ze Chiang , Yi-Hsuan Tsai , Wei-Chen Chiu

We address the problem of 3D shape completion from sparse and noisy point clouds, a fundamental problem in computer vision and robotics. Recent approaches are either data-driven or learning-based: Data-driven approaches rely on a shape…

Computer Vision and Pattern Recognition · Computer Science 2018-11-28 David Stutz , Andreas Geiger

A key question in the problem of 3D reconstruction is how to train a machine or a robot to model 3D objects. Many tasks like navigation in real-time systems such as autonomous vehicles directly depend on this problem. These systems usually…

Computer Vision and Pattern Recognition · Computer Science 2022-09-22 AmirHossein Zamani , Amir G. Aghdam , Kamran Ghaffari T

Although unsupervised feature learning has demonstrated its advantages to reducing the workload of data labeling and network design in many fields, existing unsupervised 3D learning methods still cannot offer a generic network for various…

Computer Vision and Pattern Recognition · Computer Science 2021-03-15 Peng-Shuai Wang , Yu-Qi Yang , Qian-Fang Zou , Zhirong Wu , Yang Liu , Xin Tong

Deep learning techniques for point clouds have achieved strong performance on a range of 3D vision tasks. However, it is costly to annotate large-scale point sets, making it critical to learn generalizable representations that can transfer…

Computer Vision and Pattern Recognition · Computer Science 2022-04-18 Chao Huang , Zhangjie Cao , Yunbo Wang , Jianmin Wang , Mingsheng Long

Point cloud completion aims to recover the complete 3D shape of an object from partial observations. While approaches relying on synthetic shape priors achieved promising results in this domain, their applicability and generalizability to…

Computer Vision and Pattern Recognition · Computer Science 2024-09-17 Başak Melis Öcal , Maxim Tatarchenko , Sezer Karaoglu , Theo Gevers

3D point clouds are a crucial type of data collected by LiDAR sensors and widely used in transportation applications due to its concise descriptions and accurate localization. Deep neural networks (DNNs) have achieved remarkable success in…

Computer Vision and Pattern Recognition · Computer Science 2023-05-25 Changyu Zeng , Wei Wang , Anh Nguyen , Yutao Yue

3D shape completion for real data is important but challenging, since partial point clouds acquired by real-world sensors are usually sparse, noisy and unaligned. Different from previous methods, we address the problem of learning 3D…

Computer Vision and Pattern Recognition · Computer Science 2020-08-21 Jiayuan Gu , Wei-Chiu Ma , Sivabalan Manivasagam , Wenyuan Zeng , Zihao Wang , Yuwen Xiong , Hao Su , Raquel Urtasun

Point cloud completion aims to reconstruct complete shapes from partial observations. Although current methods have achieved remarkable performance, they still have some limitations: Supervised methods heavily rely on ground truth, which…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Jingjing Lu , Huilong Pi , Yunchuan Qin , Zhuo Tang , Ruihui Li

Learning to generate 3D point clouds without 3D supervision is an important but challenging problem. Current solutions leverage various differentiable renderers to project the generated 3D point clouds onto a 2D image plane, and train deep…

Computer Vision and Pattern Recognition · Computer Science 2021-08-10 Chen Chao , Zhizhong Han , Yu-Shen Liu , Matthias Zwicker

Reconstructing 3D models from 2D images is one of the fundamental problems in computer vision. In this work, we propose a deep learning technique for 3D object reconstruction from a single image. Contrary to recent works that either use 3D…

Computer Vision and Pattern Recognition · Computer Science 2020-05-06 K L Navaneet , Ansu Mathew , Shashank Kashyap , Wei-Chih Hung , Varun Jampani , R. Venkatesh Babu

Transfer learning has long been a key factor in the advancement of many fields including 2D image analysis. Unfortunately, its applicability in 3D data processing has been relatively limited. While several approaches for point cloud…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Souhail Hadgi , Lei Li , Maks Ovsjanikov

Point clouds have attracted increasing attention. Significant progress has been made in methods for point cloud analysis, which often requires costly human annotation as supervision. To address this issue, we propose a novel…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Bi'an Du , Xiang Gao , Wei Hu , Xin Li

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…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Andrej Janda , Brandon Wagstaff , Edwin G. Ng , Jonathan Kelly