中文
相关论文

相关论文: Invaria: Learning Scale and Density Invariance in …

200 篇论文

Transformer plays an increasingly important role in various computer vision areas and remarkable achievements have also been made in point cloud analysis. Since they mainly focus on point-wise transformer, an adaptive channel encoding…

计算机视觉与模式识别 · 计算机科学 2022-07-19 Guoquan Xu , Hezhi Cao , Yifan Zhang , Yanxin Ma , Jianwei Wan , Ke Xu

The irregularity and permutation invariance of point cloud data pose challenges for effective learning. Conventional methods for addressing this issue involve converting raw point clouds to intermediate representations such as 3D voxel…

计算机视觉与模式识别 · 计算机科学 2023-06-29 Athrva Atul Pandhare

We present a new permutation-invariant network for 3D point cloud processing. Our network is composed of a recurrent set encoder and a convolutional feature aggregator. Given an unordered point set, the encoder firstly partitions its…

计算机视觉与模式识别 · 计算机科学 2019-11-26 Pengxiang Wu , Chao Chen , Jingru Yi , Dimitris Metaxas

Computer vision research has long aimed to build systems that are robust to spatial transformations found in natural data. Traditionally, this is done using data augmentation or hard-coding invariances into the architecture. However, too…

计算机视觉与模式识别 · 计算机科学 2024-02-19 Utkarsh Singhal , Carlos Esteves , Ameesh Makadia , Stella X. Yu

Recent advances in self-supervised learning (SSL) for point clouds have substantially improved 3D scene understanding without human annotations. Existing approaches emphasize semantic awareness by enforcing feature consistency across…

计算机视觉与模式识别 · 计算机科学 2026-04-01 Bin Yang , Mohamed Abdelsamad , Miao Zhang , Alexandru Paul Condurache

Extending the translation equivariance property of convolutional neural networks to larger symmetry groups has been shown to reduce sample complexity and enable more discriminative feature learning. Further, exploiting additional symmetries…

计算机视觉与模式识别 · 计算机科学 2025-02-12 Lisa Weijler , Pedro Hermosilla

Convolutional Neural Networks (CNNs) have achieved promising results in medical image segmentation. However, CNNs require lots of training data and are incapable of handling pose and deformation of objects. Furthermore, their pooling layers…

计算机视觉与模式识别 · 计算机科学 2022-06-28 Minh Tran , Viet-Khoa Vo-Ho , Ngan T. H. Le

The recent advancements in point cloud learning have enabled intelligent vehicles and robots to comprehend 3D environments better. However, processing large-scale 3D scenes remains a challenging problem, such that efficient downsampling…

计算机视觉与模式识别 · 计算机科学 2024-08-06 Hongcheng Yang , Dingkang Liang , Dingyuan Zhang , Zhe Liu , Zhikang Zou , Xingyu Jiang , Yingying Zhu

In contrast to extensive studies on general vision, pre-training for scalable visual autonomous driving remains seldom explored. Visual autonomous driving applications require features encompassing semantics, 3D geometry, and temporal…

计算机视觉与模式识别 · 计算机科学 2024-01-01 Zetong Yang , Li Chen , Yanan Sun , Hongyang Li

Point clouds are an increasingly relevant data type but they are often corrupted by noise. We propose a deep neural network based on graph-convolutional layers that can elegantly deal with the permutation-invariance problem encountered by…

计算机视觉与模式识别 · 计算机科学 2020-07-07 Francesca Pistilli , Giulia Fracastoro , Diego Valsesia , Enrico Magli

Vision-Language-Action (VLA) models excel at robotic tasks by leveraging large-scale 2D vision-language pretraining, but their reliance on RGB images limits spatial reasoning critical for real-world interaction. Retraining these models with…

机器人学 · 计算机科学 2025-03-11 Chengmeng Li , Junjie Wen , Yan Peng , Yaxin Peng , Feifei Feng , Yichen Zhu

For autonomous driving, radar sensors provide superior reliability regardless of weather conditions as well as a significantly high detection range. State-of-the-art algorithms for environment perception based on radar scans build up on…

计算机视觉与模式识别 · 计算机科学 2023-05-23 Marco Braun , Alessandro Cennamo , Markus Schoeler , Kevin Kollek , Anton Kummert

Point cloud segmentation (PCS) aims to make per-point predictions and enables robots and autonomous driving cars to understand the environment. The range image is a dense representation of a large-scale outdoor point cloud, and segmentation…

计算机视觉与模式识别 · 计算机科学 2024-08-06 Bike Chen , Chen Gong , Antti Tikanmäki , Juha Röning

A number of machine learning tasks entail a high degree of invariance: the data distribution does not change if we act on the data with a certain group of transformations. For instance, labels of images are invariant under translations of…

机器学习 · 统计学 2021-03-01 Song Mei , Theodor Misiakiewicz , Andrea Montanari

We propose a deep autoencoder with graph topology inference and filtering to achieve compact representations of unorganized 3D point clouds in an unsupervised manner. Many previous works discretize 3D points to voxels and then use…

计算机视觉与模式识别 · 计算机科学 2020-02-19 Siheng Chen , Chaojing Duan , Yaoqing Yang , Duanshun Li , Chen Feng , Dong Tian

Point clouds analysis has grasped researchers' eyes in recent years, while 3D semantic segmentation remains a problem. Most deep point clouds models directly conduct learning on 3D point clouds, which will suffer from the severe sparsity…

计算机视觉与模式识别 · 计算机科学 2021-09-21 Zhenhong Zou , Yizhe Li

As two fundamental representation modalities of 3D objects, 3D point clouds and multi-view 2D images record shape information from different domains of geometric structures and visual appearances. In the current deep learning era,…

计算机视觉与模式识别 · 计算机科学 2023-06-16 Qijian Zhang , Junhui Hou , Yue Qian

Most scanning LiDAR sensors generate a sequence of point clouds in real-time. While conventional 3D object detectors use a set of unordered LiDAR points acquired over a fixed time interval, recent studies have revealed that substantial…

计算机视觉与模式识别 · 计算机科学 2022-12-22 Junho Koh , Junhyung Lee , Youngwoo Lee , Jaekyum Kim , Jun Won Choi

Transformer-based end-to-end speech recognition has achieved great success. However, the large footprint and computational overhead make it difficult to deploy these models in some real-world applications. Model compression techniques can…

计算与语言 · 计算机科学 2023-03-15 Yifan Peng , Jaesong Lee , Shinji Watanabe

Point cloud data now are popular data representations in a number of three-dimensional (3D) vision research realms. However, due to the limited performance of sensors and sensing noise, the raw data usually suffer from sparsity, noise, and…

计算机视觉与模式识别 · 计算机科学 2024-11-05 Siwen Quan , Junhao Yu , Ziming Nie , Muze Wang , Sijia Feng , Pei An , Jiaqi Yang