English
Related papers

Related papers: Universal Correspondence Network

200 papers

X-ray computed tomography (CT) using sparse projection views is a recent approach to reduce the radiation dose. However, due to the insufficient projection views, an analytic reconstruction approach using the filtered back projection (FBP)…

Computer Vision and Pattern Recognition · Computer Science 2018-03-29 Yoseob Han , Jong Chul Ye

In this article we investigate the efficiency of deep learning algorithms in solving the task of detecting anatomical reference points on radiological images of the head in lateral projection using a fully convolutional neural network and a…

Image and Video Processing · Electrical Eng. & Systems 2020-06-19 Konstantin Dobratulin , Andrey Gaidel , Irina Aupova , Anna Ivleva , Aleksandr Kapishnikov , Pavel Zelter

We present a new approach to unsupervised shape correspondence learning between pairs of point clouds. We make the first attempt to adapt the classical locally linear embedding algorithm (LLE) -- originally designed for nonlinear…

Computer Vision and Pattern Recognition · Computer Science 2022-09-08 Pan He , Patrick Emami , Sanjay Ranka , Anand Rangarajan

Establishing correspondences across images is a fundamental challenge in computer vision, underpinning tasks like Structure-from-Motion, image editing, and point tracking. Traditional methods are often specialized for specific…

Computer Vision and Pattern Recognition · Computer Science 2025-01-28 Fei Xue , Sven Elflein , Laura Leal-Taixé , Qunjie Zhou

Convolutional Neural Network (CNN) features have been successfully employed in recent works as an image descriptor for various vision tasks. But the inability of the deep CNN features to exhibit invariance to geometric transformations and…

Computer Vision and Pattern Recognition · Computer Science 2015-04-27 Konda Reddy Mopuri , R. Venkatesh Babu

Motivated by the intuition that one can transform two aligned point clouds to each other more easily and meaningfully than a misaligned pair, we propose CorrNet3D -- the first unsupervised and end-to-end deep learning-based framework -- to…

Computer Vision and Pattern Recognition · Computer Science 2021-05-04 Yiming Zeng , Yue Qian , Zhiyu Zhu , Junhui Hou , Hui Yuan , Ying He

How to extract significant point cloud features and estimate the pose between them remains a challenging question, due to the inherent lack of structure and ambiguous order permutation of point clouds. Despite significant improvements in…

Computer Vision and Pattern Recognition · Computer Science 2021-12-14 Zhu Xu , Zhengyao Bai , Huijie Liu , Qianjie Lu , Shenglan Fan

In the last two years, convolutional neural networks (CNNs) have achieved an impressive suite of results on standard recognition datasets and tasks. CNN-based features seem poised to quickly replace engineered representations, such as SIFT…

Computer Vision and Pattern Recognition · Computer Science 2014-09-23 Pulkit Agrawal , Ross Girshick , Jitendra Malik

Deep Convolutional Neural Networks (DCNNs) commonly use generic `max-pooling' (MP) layers to extract deformation-invariant features, but we argue in favor of a more refined treatment. First, we introduce epitomic convolution as a building…

Computer Vision and Pattern Recognition · Computer Science 2014-12-02 George Papandreou , Iasonas Kokkinos , Pierre-André Savalle

Estimating dense correspondences between images is a long-standing image under-standing task. Recent works introduce convolutional neural networks (CNNs) to extract high-level feature maps and find correspondences through feature matching.…

Computer Vision and Pattern Recognition · Computer Science 2020-08-14 Hao Huang , Jianchun Chen , Xiang Li , Lingjing Wang , Yi Fang

Convolutional neural networks have enabled major progresses in addressing pixel-level prediction tasks such as semantic segmentation, depth estimation, surface normal prediction and so on, benefiting from their powerful capabilities in…

Computer Vision and Pattern Recognition · Computer Science 2021-12-16 Guanglei Yang , Paolo Rota , Xavier Alameda-Pineda , Dan Xu , Mingli Ding , Elisa Ricci

This paper presents a deep architecture for dense semantic correspondence, called pyramidal affine regression networks (PARN), that estimates locally-varying affine transformation fields across images. To deal with intra-class appearance…

Computer Vision and Pattern Recognition · Computer Science 2018-08-02 Sangryul Jeon , Seungryong Kim , Dongbo Min , Kwanghoon Sohn

Encoder-decoder networks using convolutional neural network (CNN) architecture have been extensively used in deep learning literatures thanks to its excellent performance for various inverse problems. However, it is still difficult to…

Machine Learning · Computer Science 2019-05-08 Jong Chul Ye , Woon Kyoung Sung

We propose a way to learn visual features that are compatible with previously computed ones even when they have different dimensions and are learned via different neural network architectures and loss functions. Compatible means that, if…

Computer Vision and Pattern Recognition · Computer Science 2021-01-07 Yantao Shen , Yuanjun Xiong , Wei Xia , Stefano Soatto

We investigate the problem of pixelwise correspondence for deformable objects, namely cloth and rope, by comparing both classical and learning-based methods. We choose cloth and rope because they are traditionally some of the most difficult…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Priya Sundaresan , Aditya Ganapathi , Harry Zhang , Shivin Devgon

Conventional techniques to establish dense correspondences across visually or semantically similar images focused on designing a task-specific matching prior, which is difficult to model. To overcome this, recent learning-based methods have…

Computer Vision and Pattern Recognition · Computer Science 2021-12-16 Sunghwan Hong , Seungryong Kim

Recent success in training deep neural networks have prompted active investigation into the features learned on their intermediate layers. Such research is difficult because it requires making sense of non-linear computations performed by…

Machine Learning · Computer Science 2016-03-01 Yixuan Li , Jason Yosinski , Jeff Clune , Hod Lipson , John Hopcroft

A major area of growth within deep learning has been the study and implementation of convolutional neural networks. The general explanation within the deep learning community of the robustness of convolutional neural networks (CNNs) within…

Computer Vision and Pattern Recognition · Computer Science 2018-09-18 Kian Ghodoussi , Nihar Sheth , Zane Durante , Markie Wagner

Most invariance-based self-supervised methods rely on single object-centric images (e.g., ImageNet images) for pretraining, learning features that invariant to geometric transformation. However, when images are not object-centric, the…

Computer Vision and Pattern Recognition · Computer Science 2023-05-18 Taeho Kim , Jong-Min Lee

Given a pedestrian image as a query, the purpose of person re-identification is to identify the correct match from a large collection of gallery images depicting the same person captured by disjoint camera views. The critical challenge is…

Computer Vision and Pattern Recognition · Computer Science 2017-12-05 Lin Wu , Yang Wang