English
Related papers

Related papers: DCVNet: Dilated Cost Volume Networks for Fast Opti…

200 papers

Optical flow estimation is an essential step for many real-world computer vision tasks. Existing deep networks have achieved satisfactory results by mostly employing a pyramidal coarse-to-fine paradigm, where a key process is to adopt…

Computer Vision and Pattern Recognition · Computer Science 2021-02-02 Lingtong Kong , Xiaohang Yang , Jie Yang

Inspired by frame-based methods, state-of-the-art event-based optical flow networks rely on the explicit construction of correlation volumes, which are expensive to compute and store, rendering them unsuitable for robotic applications with…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 Yilun Wu , Federico Paredes-Vallés , Guido C. H. E. de Croon

Existing state-of-the-art disparity estimation works mostly leverage the 4D concatenation volume and construct a very deep 3D convolution neural network (CNN) for disparity regression, which is inefficient due to the high memory consumption…

Computer Vision and Pattern Recognition · Computer Science 2021-03-05 Songyan Zhang , Zhicheng Wang , Qiang Wang , Jinshuo Zhang , Gang Wei , Xiaowen Chu

Optical flow is inherently a 2D search problem, and thus the computational complexity grows quadratically with respect to the search window, making large displacements matching infeasible for high-resolution images. In this paper, we take…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Haofei Xu , Jiaolong Yang , Jianfei Cai , Juyong Zhang , Xin Tong

Brain tumor segmentation plays a pivotal role in medical image processing. In this work, we aim to segment brain MRI volumes. 3D convolution neural networks (CNN) such as 3D U-Net and V-Net employing 3D convolutions to capture the…

Computer Vision and Pattern Recognition · Computer Science 2019-09-24 Chen Chen , Xiaopeng Liu , Meng Ding , Junfeng Zheng , Jiangyun Li

Stereo matching is essential for robot navigation. However, the accuracy of current widely used traditional methods is low, while methods based on CNN need expensive computational cost and running time. This is because different cost…

Computer Vision and Pattern Recognition · Computer Science 2021-03-16 Xiaogang Jia , Wei Chen , Zhengfa Liang , Mingfei Wu , Yusong Tan , Libo Huang

Recent learning-based methods for event-based optical flow estimation utilize cost volumes for pixel matching but suffer from redundant computations and limited scalability to higher resolutions for flow refinement. In this work, we take…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Daikun Liu , Lei Cheng , Teng Wang , changyin Sun

Classical approaches for estimating optical flow have achieved rapid progress in the last decade. However, most of them are too slow to be applied in real-time video analysis. Due to the great success of deep learning, recent work has…

Computer Vision and Pattern Recognition · Computer Science 2017-07-21 Yi Zhu , Shawn Newsam

In recent years, using a deep convolutional neural network (CNN) as a feature encoder (or backbone) is the most commonly observed architectural pattern in several computer vision methods, and semantic segmentation is no exception. The two…

Computer Vision and Pattern Recognition · Computer Science 2021-09-22 Venkata Satya Sai Ajay Daliparthi

Swept Volume (SV), the volume displaced by an object when it is moving along a trajectory, is considered a useful metric for motion planning. First, SV has been used to identify collisions along a trajectory, because it directly measures…

Robotics · Computer Science 2018-05-30 Hao-Tien Lewis Chiang , Aleksandra Faust , Lydia Tapia

Semantic segmentation has achieved remarkable results with high computational cost and a large number of parameters. However, real-world applications require efficient inference speed on embedded devices. Most previous works address the…

Computer Vision and Pattern Recognition · Computer Science 2020-10-22 Xinneng Yang , Yan Wu , Junqiao Zhao , Feilin Liu

We propose to incorporate feature correlation and sequential processing into dense optical flow estimation from event cameras. Modern frame-based optical flow methods heavily rely on matching costs computed from feature correlation. In…

Computer Vision and Pattern Recognition · Computer Science 2021-10-22 Mathias Gehrig , Mario Millhäusler , Daniel Gehrig , Davide Scaramuzza

In this paper, we present a detailed design of dynamic video segmentation network (DVSNet) for fast and efficient semantic video segmentation. DVSNet consists of two convolutional neural networks: a segmentation network and a flow network.…

Computer Vision and Pattern Recognition · Computer Science 2018-06-15 Yu-Syuan Xu , Tsu-Jui Fu , Hsuan-Kung Yang , Chun-Yi Lee

FlowNet2, the state-of-the-art convolutional neural network (CNN) for optical flow estimation, requires over 160M parameters to achieve accurate flow estimation. In this paper we present an alternative network that outperforms FlowNet2 on…

Computer Vision and Pattern Recognition · Computer Science 2018-05-24 Tak-Wai Hui , Xiaoou Tang , Chen Change Loy

Convolutional Neural Networks (CNNs) have become indispensable for solving machine learning tasks in speech recognition, computer vision, and other areas that involve high-dimensional data. A CNN filters the input feature using a network…

Machine Learning · Computer Science 2020-02-13 Jonathan Ephrath , Moshe Eliasof , Lars Ruthotto , Eldad Haber , Eran Treister

The tradeoff between receptive field size and efficiency is a crucial issue in low level vision. Plain convolutional networks (CNNs) generally enlarge the receptive field at the expense of computational cost. Recently, dilated filtering has…

Computer Vision and Pattern Recognition · Computer Science 2018-05-23 Pengju Liu , Hongzhi Zhang , Kai Zhang , Liang Lin , Wangmeng Zuo

We introduce a View-Volume convolutional neural network (VVNet) for inferring the occupancy and semantic labels of a volumetric 3D scene from a single depth image. The VVNet concatenates a 2D view CNN and a 3D volume CNN with a…

Computer Vision and Pattern Recognition · Computer Science 2018-06-15 Yu-Xiao Guo , Xin Tong

Multiview stereo aims to reconstruct scene depth from images acquired by a camera under arbitrary motion. Recent methods address this problem through deep learning, which can utilize semantic cues to deal with challenges such as textureless…

Computer Vision and Pattern Recognition · Computer Science 2019-05-03 Sunghoon Im , Hae-Gon Jeon , Stephen Lin , In So Kweon

Stereo matching is a fundamental building block for many vision and robotics applications. An informative and concise cost volume representation is vital for stereo matching of high accuracy and efficiency. In this paper, we present a novel…

Computer Vision and Pattern Recognition · Computer Science 2022-06-24 Gangwei Xu , Junda Cheng , Peng Guo , Xin Yang

The ability to process and act on data in real time is increasingly critical for applications ranging from autonomous vehicles, three-dimensional environmental sensing and remote robotics. However, the deployment of deep neural networks…