English
Related papers

Related papers: D3Former: Jointly Learning Repeatable Dense Detect…

200 papers

Multi-task networks can potentially improve performance and computational efficiency compared to single-task networks, facilitating online deployment. However, current multi-task architectures in point cloud perception combine multiple…

Computer Vision and Pattern Recognition · Computer Science 2024-04-22 Christopher Lang , Alexander Braun , Lars Schillingmann , Abhinav Valada

Remarkable advancements have been made recently in point cloud analysis through the exploration of transformer architecture, but it remains challenging to effectively learn local and global structures within point clouds. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2023-11-01 Haibo Qiu , Baosheng Yu , Dacheng Tao

3D point-cloud recognition with PointNet and its variants has received remarkable progress. A missing ingredient, however, is the ability to automatically evaluate point-wise importance w.r.t.\! classification performance, which is usually…

Computer Vision and Pattern Recognition · Computer Science 2019-09-16 Tianhang Zheng , Changyou Chen , Junsong Yuan , Bo Li , Kui Ren

Recent advancements in vision-language pre-training (e.g. CLIP) have shown that vision models can benefit from language supervision. While many models using language modality have achieved great success on 2D vision tasks, the joint…

Computer Vision and Pattern Recognition · Computer Science 2023-01-19 Rui Huang , Xuran Pan , Henry Zheng , Haojun Jiang , Zhifeng Xie , Shiji Song , Gao Huang

Point clouds and images could provide complementary information when representing 3D objects. Fusing the two kinds of data usually helps to improve the detection results. However, it is challenging to fuse the two data modalities, due to…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Xun Tan , Xingyu Chen , Guowei Zhang , Jishiyu Ding , Xuguang Lan

The current trend in computer vision is to utilize one universal model to address all various tasks. Achieving such a universal model inevitably requires incorporating multi-domain data for joint training to learn across multiple problem…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Zhenyu Wang , Yali Li , Hengshuang Zhao , Shengjin Wang

Estimating probability density and its score from samples remains a core problem in generative modeling, Bayesian inference, and kinetic theory. Existing methods are bifurcated: classical kernel density estimators (KDE) generalize across…

Machine Learning · Computer Science 2026-05-29 Vasily Ilin , Peter Sushko , Ranjay Krishna

Semantic pattern of an object point cloud is determined by its topological configuration of local geometries. Learning discriminative representations can be challenging due to large shape variations of point sets in local regions and…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Longkun Zou , Wanru Zhu , Ke Chen , Lihua Guo , Kailing Guo , Kui Jia , Yaowei Wang

Our paper addresses the problem of models struggling to learn diverse features, due to either forgetting previously learned features or failing to learn new ones. To overcome this problem, we introduce Diverse Feature Learning (DFL), a…

Artificial Intelligence · Computer Science 2024-04-01 Sejik Park

Pre-trained large-scale models have exhibited remarkable efficacy in computer vision, particularly for 2D image analysis. However, when it comes to 3D point clouds, the constrained accessibility of data, in contrast to the vast repositories…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Mengke Li , Da Li , Guoqing Yang , Yiu-ming Cheung , Hui Huang

Multimodal 3D object detection based on deep neural networks has indeed made significant progress. However, it still faces challenges due to the misalignment of scale and spatial information between features extracted from 2D images and…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Bonan Ding , Jin Xie , Jing Nie , Jiale Cao

Recently, heatmap regression methods based on 1D landmark representations have shown prominent performance on locating facial landmarks. However, previous methods ignored to make deep explorations on the good potentials of 1D landmark…

Computer Vision and Pattern Recognition · Computer Science 2024-02-02 Shi Yin , Shijie Huan , Shangfei Wang , Jinshui Hu , Tao Guo , Bing Yin , Baocai Yin , Cong Liu

Point-pixel registration between LiDAR point clouds and camera images is a fundamental yet challenging task in autonomous driving and robotic perception. A key difficulty lies in the modality gap between unstructured point clouds and…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Yu Han , Zhiwei Huang , Yanting Zhang , Fangjun Ding , Shen Cai , Rui Fan

4D millimeter-wave (mmWave) radar has been widely adopted in autonomous driving and robot perception due to its low cost and all-weather robustness. However, point-cloud-based radar representations suffer from information loss due to…

Computer Vision and Pattern Recognition · Computer Science 2026-01-16 Runwei Guan , Jianan Liu , Shaofeng Liang , Fangqiang Ding , Shanliang Yao , Xiaokai Bai , Daizong Liu , Tao Huang , Guoqiang Mao , Hui Xiong

3D anomaly detection in point-cloud data is critical for industrial quality control, aiming to identify structural defects with high reliability. However, current memory bank-based methods often suffer from inconsistent feature…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Yuyang Yu , Zhengwei Chen , Xuemiao Xu , Lei Zhang , Haoxin Yang , Yongwei Nie , Shengfeng He

In the context of 2D/3D registration, this paper introduces an approach that allows to match features detected in two different modalities: photographs and 3D models, by using a common 2D reprensentation. More precisely, 2D images are…

Computer Vision and Pattern Recognition · Computer Science 2019-07-24 Hatem A. Rashwan , Sylvie Chambon , Pierre Gurdjos , Géraldine Morin , Vincent Charvillat

In this paper, we propose the 3DFeat-Net which learns both 3D feature detector and descriptor for point cloud matching using weak supervision. Unlike many existing works, we do not require manual annotation of matching point clusters.…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Zi Jian Yew , Gim Hee Lee

Sparse keypoint matching based on distinct 3D feature representations can improve the efficiency and robustness of point cloud registration. Existing learning-based 3D descriptors and keypoint detectors are either independent or loosely…

Computer Vision and Pattern Recognition · Computer Science 2024-02-13 Renlang Huang , Minglei Zhao , Jiming Chen , Liang Li

This paper introduces a new problem in 3D point cloud: few-shot instance segmentation. Given a few annotated point clouds exemplified a target class, our goal is to segment all instances of this target class in a query point cloud. This…

Computer Vision and Pattern Recognition · Computer Science 2022-08-09 Tuan Ngo , Khoi Nguyen

Semantic parsing of large-scale 3D point clouds is an important research topic in computer vision and remote sensing fields. Most existing approaches utilize hand-crafted features for each modality independently and combine them in a…

Computer Vision and Pattern Recognition · Computer Science 2017-07-24 Fangyu Liu , Shuaipeng Li , Liqiang Zhang , Chenghu Zhou , Rongtian Ye , Yuebin Wang , Jiwen Lu