English
Related papers

Related papers: Shift Convolution Network for Stereo Matching

200 papers

Video stereo matching is the task of estimating consistent disparity maps from rectified stereo videos. There is considerable scope for improvement in both datasets and methods within this area. Recent learning-based methods often focus on…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Junpeng Jing , Ye Mao , Anlan Qiu , Krystian Mikolajczyk

Transformer and its variants have shown great potential for various vision tasks in recent years, including image classification, object detection and segmentation. Meanwhile, recent studies also reveal that with proper architecture design,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Xinghao Chen , Siwei Li , Yijing Yang , Yunhe Wang

Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that…

Machine Learning · Computer Science 2020-09-14 Mingxing Tan , Quoc V. Le

Up-to-date High-Definition (HD) maps are essential for self-driving cars. To achieve constantly updated HD maps, we present a deep neural network (DNN), Diff-Net, to detect changes in them. Compared to traditional methods based on object…

Computer Vision and Pattern Recognition · Computer Science 2021-10-19 Lei He , Shengjie Jiang , Xiaoqing Liang , Ning Wang , Shiyu Song

At present, the great achievements of convolutional neural network(CNN) in feature and metric learning have attracted many researchers. However, the vast majority of deep network architectures have been used to represent based on real…

Computer Vision and Pattern Recognition · Computer Science 2019-03-26 Siwen Jiang , Wenxuan Wei , Shihao Guo , Hongguang Fu , Lei Huang

Learning-based multi-view stereo (MVS) methods have made impressive progress and surpassed traditional methods in recent years. However, their accuracy and completeness are still struggling. In this paper, we propose a new method to enhance…

Computer Vision and Pattern Recognition · Computer Science 2022-06-22 Yikang Ding , Zhenyang Li , Dihe Huang , Zhiheng Li , Kai Zhang

Recent work has shown that depth estimation from a stereo pair of images can be formulated as a supervised learning task to be resolved with convolutional neural networks (CNNs). However, current architectures rely on patch-based Siamese…

Computer Vision and Pattern Recognition · Computer Science 2018-03-26 Jia-Ren Chang , Yong-Sheng Chen

In this paper, we propose a learning-based image fragment pair-searching and -matching approach to solve the challenging restoration problem. Existing works use rule-based methods to match similar contour shapes or textures, which are…

Computer Vision and Pattern Recognition · Computer Science 2025-01-23 Rixin Zhou , Ding Xia , Yi Zhang , Honglin Pang , Xi Yang , Chuntao Li

Deep convolutional neural networks trained end-to-end are the state-of-the-art methods to regress dense disparity maps from stereo pairs. These models, however, suffer from a notable decrease in accuracy when exposed to scenarios…

Computer Vision and Pattern Recognition · Computer Science 2019-04-08 Alessio Tonioni , Fabio Tosi , Matteo Poggi , Stefano Mattoccia , Luigi Di Stefano

In this paper, we propose an effective method for fast and accurate scene parsing called Bidirectional Alignment Network (BiAlignNet). Previously, one representative work BiSeNet~\cite{bisenet} uses two different paths (Context Path and…

Computer Vision and Pattern Recognition · Computer Science 2021-05-26 Yanran Wu , Xiangtai Li , Chen Shi , Yunhai Tong , Yang Hua , Tao Song , Ruhui Ma , Haibing Guan

Semantic segmentation requires both rich spatial information and sizeable receptive field. However, modern approaches usually compromise spatial resolution to achieve real-time inference speed, which leads to poor performance. In this…

Computer Vision and Pattern Recognition · Computer Science 2018-08-03 Changqian Yu , Jingbo Wang , Chao Peng , Changxin Gao , Gang Yu , Nong Sang

Convolution is a central operation in Convolutional Neural Networks (CNNs), which applies a kernel to overlapping regions shifted across the image. However, because of the strong correlations in real-world image data, convolutional kernels…

Visual attention modeling has recently gained momentum in developing visual hierarchies provided by Convolutional Neural Networks. Despite recent successes of feedforward processing on the abstraction of concepts form raw images, the…

Computer Vision and Pattern Recognition · Computer Science 2017-08-23 Mahdi Biparva , John Tsotsos

The channel redundancy in feature maps of convolutional neural networks (CNNs) results in the large consumption of memories and computational resources. In this work, we design a novel Slim Convolution (SlimConv) module to boost the…

Computer Vision and Pattern Recognition · Computer Science 2021-09-08 Jiaxiong Qiu , Cai Chen , Shuaicheng Liu , Bing Zeng

Knowledge distillation has been quite popular in vision for tasks like classification and segmentation however not much work has been done for distilling state-of-the-art stereo matching methods despite their range of applications. One of…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Rafia Rahim , Samuel Woerz , Andreas Zell

Under stereo settings, the problem of image super-resolution (SR) and disparity estimation are interrelated that the result of each problem could help to solve the other. The effective exploitation of correspondence between different views…

Computer Vision and Pattern Recognition · Computer Science 2021-06-03 Qinyan Dai , Juncheng Li , Qiaosi Yi , Faming Fang , Guixu Zhang

This work introduces a novel method for surface normal estimation from rectified stereo image pairs, leveraging affine transformations derived from disparity values to achieve fast and accurate results. We demonstrate how the rectification…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Csongor Csanad Kariko , Muhammad Rafi Faisal , Levente Hajder

Person Re-Identification (ReID) requires comparing two images of person captured under different conditions. Existing work based on neural networks often computes the similarity of feature maps from one single convolutional layer. In this…

Computer Vision and Pattern Recognition · Computer Science 2018-04-03 Yiluan Guo , Ngai-Man Cheung

Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance on many visual recognition tasks. However, the combination of convolution and pooling operations only shows invariance to small local location changes in…

Computer Vision and Pattern Recognition · Computer Science 2019-12-02 Xu Shen , Xinmei Tian , Shaoyan Sun , Dacheng Tao

Vision transformers have been successfully applied to image recognition tasks due to their ability to capture long-range dependencies within an image. However, there are still gaps in both performance and computational cost between…

Computer Vision and Pattern Recognition · Computer Science 2022-06-15 Jianyuan Guo , Kai Han , Han Wu , Yehui Tang , Xinghao Chen , Yunhe Wang , Chang Xu