English
Related papers

Related papers: SIMPC: Learning Self-Induced Mirror-Point Consiste…

200 papers

This paper proposes a new method to infer keypoints from arbitrary object categories in practical scenarios where point cloud data (PCD) are noisy, down-sampled and arbitrarily rotated. Our proposed model adheres to the following…

Computer Vision and Pattern Recognition · Computer Science 2023-08-11 Mohammad Zohaib , Alessio Del Bue

Removing outlier correspondences is one of the critical steps for successful feature-based point cloud registration. Despite the increasing popularity of introducing deep learning methods in this field, spatial consistency, which is…

Computer Vision and Pattern Recognition · Computer Science 2021-03-10 Xuyang Bai , Zixin Luo , Lei Zhou , Hongkai Chen , Lei Li , Zeyu Hu , Hongbo Fu , Chiew-Lan Tai

Semantic analyses of object point clouds are largely driven by releasing of benchmarking datasets, including synthetic ones whose instances are sampled from object CAD models. However, learning from synthetic data may not generalize to…

Computer Vision and Pattern Recognition · Computer Science 2022-07-20 Yongwei Chen , Zihao Wang , Longkun Zou , Ke Chen , Kui Jia

3D dynamic point clouds provide a discrete representation of real-world objects or scenes in motion, which have been widely applied in immersive telepresence, autonomous driving, surveillance, etc. However, point clouds acquired from…

Computer Vision and Pattern Recognition · Computer Science 2022-04-20 Qianjiang Hu , Wei Hu

Current self-supervised denoising methods for paired noisy images typically involve mapping one noisy image through the network to the other noisy image. However, after measuring the spectral bias of such methods using our proposed Image…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Wang Zhang , Huaqiu Li , Xiaowan Hu , Tao Jiang , Zikang Chen , Haoqian Wang

Building on recent advances in Bayesian statistics and image denoising, we propose Noise2Score3D, a fully unsupervised framework for point cloud denoising that addresses the critical challenge of limited availability of clean data.…

Computer Vision and Pattern Recognition · Computer Science 2025-06-24 Xiangbin Wei

Real noisy-clean pairs on a large scale are costly and difficult to obtain. Meanwhile, supervised denoisers trained on synthetic data perform poorly in practice. Self-supervised denoisers, which learn only from single noisy images, solve…

Image and Video Processing · Electrical Eng. & Systems 2023-05-09 Zejin Wang , Jiazheng Liu , Guoqing Li , Hua Han

Supervised neural networks are known to achieve excellent results in various image restoration tasks. However, such training requires datasets composed of pairs of corrupted images and their corresponding ground truth targets.…

Computer Vision and Pattern Recognition · Computer Science 2022-11-21 Gregory Vaksman , Michael Elad

We present a new self-supervised paradigm on point cloud sequence understanding. Inspired by the discriminative and generative self-supervised methods, we design two tasks, namely point cloud sequence based Contrastive Prediction and…

Computer Vision and Pattern Recognition · Computer Science 2023-05-23 Xiaoxiao Sheng , Zhiqiang Shen , Gang Xiao

We propose the GraphSIM -- an objective metric to accurately predict the subjective quality of point cloud with superimposed geometry and color impairments. Motivated by the facts that human vision system is more sensitive to the high…

Image and Video Processing · Electrical Eng. & Systems 2020-12-23 Qi Yang , Zhan Ma , Yiling Xu , Zhu Li , Jun Sun

Point clouds obtained with 3D scanners or by image-based reconstruction techniques are often corrupted with significant amount of noise and outliers. Traditional methods for point cloud denoising largely rely on local surface fitting (e.g.,…

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

Due to the scarcity of annotated scene flow data, self-supervised scene flow learning in point clouds has attracted increasing attention. In the self-supervised manner, establishing correspondences between two point clouds to approximate…

Computer Vision and Pattern Recognition · Computer Science 2021-05-19 Ruibo Li , Guosheng Lin , Lihua Xie

In recent years, deep learning-based point cloud normal estimation has made great progress. However, existing methods mainly rely on the PCPNet dataset, leading to overfitting. In addition, the correlation between point clouds with…

Computer Vision and Pattern Recognition · Computer Science 2024-06-25 Wei Jin , Jun Zhou , Nannan Li , Haba Madeline , Xiuping Liu

Correspondence search is an essential step in rigid point cloud registration algorithms. Most methods maintain a single correspondence at each step and gradually remove wrong correspondances. However, building one-to-one correspondence with…

Computer Vision and Pattern Recognition · Computer Science 2022-09-30 Jun-Jee Chao , Selim Engin , Nicolai Häni , Volkan Isler

Visual imitation learning with 3D point clouds has advanced robotic manipulation by providing geometry-aware, appearance-invariant observations. However, point cloud-based policies remain highly sensitive to sensor noise, pose…

Robotics · Computer Science 2026-01-27 Zhiyuan Zhang , Yu She

Establishing accurate 3D correspondences between shapes stands as a pivotal challenge with profound implications for computer vision and robotics. However, existing self-supervised methods for this problem assume perfect input shape…

Computer Vision and Pattern Recognition · Computer Science 2024-04-23 Chunghyun Park , Seungwook Kim , Jaesik Park , Minsu Cho

Learning without supervision how to predict 3D scene flows from point clouds is essential to many perception systems. We propose a novel learning framework for this task which improves the necessary regularization. Relying on the assumption…

Computer Vision and Pattern Recognition · Computer Science 2024-08-14 Patrik Vacek , David Hurych , Karel Zimmermann , Patrick Perez , Tomas Svoboda

We introduce Rectified Point Flow, a unified parameterization that formulates pairwise point cloud registration and multi-part shape assembly as a single conditional generative problem. Given unposed point clouds, our method learns a…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Tao Sun , Liyuan Zhu , Shengyu Huang , Shuran Song , Iro Armeni

We consider the problem of positioning a cloud of points in the Euclidean space $\mathbb{R}^d$, using noisy measurements of a subset of pairwise distances. This task has applications in various areas, such as sensor network localization and…

Statistics Theory · Mathematics 2012-11-22 Adel Javanmard , Andrea Montanari