English
Related papers

Related papers: Parallel Separable 3D Convolution for Video and Vo…

200 papers

Geometric feature learning for 3D surfaces is critical for many applications in computer graphics and 3D vision. However, deep learning currently lags in hierarchical modeling of 3D surfaces due to the lack of required operations and/or…

Computer Vision and Pattern Recognition · Computer Science 2023-04-25 Huan Lei , Naveed Akhtar , Mubarak Shah , Ajmal Mian

The convolutional neural network-based methods have become more and more popular for medical image segmentation due to their outstanding performance. However, they struggle with capturing long-range dependencies, which are essential for…

Image and Video Processing · Electrical Eng. & Systems 2024-01-30 Hongkun Sun , Jing Xu , Yuping Duan

This paper addresses the challenges of designing mesh convolution neural networks for 3D mesh dense prediction. While deep learning has achieved remarkable success in image dense prediction tasks, directly applying or extending these…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Shi Hezi , Jiang Luo , Zheng Jianmin , Zeng Jun

The escalating energy demands and parallel-processing bottlenecks of electronic neural networks underscore the need for alternative computing paradigms. Optical neural networks, capitalizing on the inherent parallelism and speed of light…

Existing networks directly learn feature representations on 3D point clouds for shape analysis. We argue that 3D point clouds are highly redundant and hold irregular (permutation-invariant) structure, which makes it difficult to achieve…

Machine Learning · Computer Science 2020-07-21 Sameera Ramasinghe , Salman Khan , Nick Barnes , Stephen Gould

The analysis of 3D point clouds has diverse applications in robotics, vision and graphics. Processing them presents specific challenges since they are naturally sparse, can vary in spatial resolution and are typically unordered. Graph-based…

Computer Vision and Pattern Recognition · Computer Science 2023-04-03 Mohammad Khodadad , Morteza Rezanejad , Ali Shiraee Kasmaee , Kaleem Siddiqi , Dirk Walther , Hamidreza Mahyar

Convolutional neural networks (CNNs) have been pivotal in various 2D image analysis tasks, including computer vision, image indexing and retrieval or semantic classification. Extending CNNs to 3D data such as point clouds and 3D meshes…

Computer Vision and Pattern Recognition · Computer Science 2025-01-08 Germain Bregeon , Marius Preda , Radu Ispas , Titus Zaharia

Convolutional Neural Networks (CNNs) have been regarded as the go-to models for visual recognition. More recently, convolution-free networks, based on multi-head self-attention (MSA) or multi-layer perceptrons (MLPs), become more and more…

Computer Vision and Pattern Recognition · Computer Science 2022-06-14 Zhaofan Qiu , Ting Yao , Chong-Wah Ngo , Tao Mei

Time varying sequences of 3D point clouds, or 4D point clouds, are now being acquired at an increasing pace in several applications (e.g., LiDAR in autonomous or assisted driving). In many cases, such volume of data is transmitted, thus…

Computer Vision and Pattern Recognition · Computer Science 2023-06-05 Lorenzo Berlincioni , Stefano Berretti , Marco Bertini , Alberto Del Bimbo

There is an increasing interest in applying deep learning to 3D mesh segmentation. We observe that 1) existing feature-based techniques are often slow or sensitive to feature resizing, 2) there are minimal comparative studies and 3)…

Graphics · Computer Science 2018-02-09 David George , Xianghua Xie , Gary KL Tam

Depthwise convolution has gradually become an indispensable operation for modern efficient neural networks and larger kernel sizes ($\ge5$) have been applied to it recently. In this paper, we propose a novel extremely separated…

Computer Vision and Pattern Recognition · Computer Science 2020-02-28 Jiarong Chen , Zongqing Lu , Jing-Hao Xue , Qingmin Liao

When using Convolutional Neural Networks (CNNs) for segmentation of organs and lesions in medical images, the conventional approach is to work with inputs and outputs either as single slice (2D) or whole volumes (3D). One common…

Image and Video Processing · Electrical Eng. & Systems 2020-11-17 Minh H. Vu , Guus Grimbergen , Tufve Nyholm , Tommy Löfstedt

3D CNN shows its strong ability in learning spatiotemporal representation in recent video recognition tasks. However, inflating 2D convolution to 3D inevitably introduces additional computational costs, making it cumbersome in practical…

Computer Vision and Pattern Recognition · Computer Science 2019-11-27 Pingchuan Ma , Yao Zhou , Yu Lu , Wei Zhang

The past few years have witnessed growth in the computational requirements for training deep convolutional neural networks. Current approaches parallelize training onto multiple devices by applying a single parallelization strategy (e.g.,…

Machine Learning · Computer Science 2018-06-12 Zhihao Jia , Sina Lin , Charles R. Qi , Alex Aiken

In this paper, we present a comprehensive study and propose several novel techniques for implementing 3D convolutional blocks using 2D and/or 1D convolutions with only 4D and/or 3D tensors. Our motivation is that 3D convolutions with 5D…

Computer Vision and Pattern Recognition · Computer Science 2024-07-24 Habib Hajimolahoseini , Walid Ahmed , Austin Wen , Yang Liu

With the development of the super-resolution convolutional neural network (SRCNN), deep learning technique has been widely applied in the field of image super-resolution. Previous works mainly focus on optimizing the structure of SRCNN,…

Computer Vision and Pattern Recognition · Computer Science 2020-08-26 Jianwei Zhang , zhenxing Wang , yuhui Zheng , Guoqing Zhang

Volumetric video enables immersive and interactive visual experiences by supporting free viewpoint exploration and realistic motion parallax. However, existing volumetric representations from explicit point clouds to implicit neural fields,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-20 Kaiyuan Hu , Yili Jin , Junhua Liu , Xize Duan , Hong Kang , Xue Liu

The convolution operation is a central building block of neural network architectures widely used in computer vision. The size of the convolution kernels determines both the expressiveness of convolutional neural networks (CNN), as well as…

Image and Video Processing · Electrical Eng. & Systems 2022-10-10 Tianyu Ma , Adrian V. Dalca , Mert R. Sabuncu

Convolutional neural networks are state-of-the-art for various segmentation tasks. While for 2D images these networks are also computationally efficient, 3D convolutions have huge storage requirements and require long training time. To…

Computer Vision and Pattern Recognition · Computer Science 2019-08-06 Christoph Angermann , Markus Haltmeier , Ruth Steiger , Sergiy Pereverzyev , Elke Gizewski

The segmentation of organs in volumetric medical images plays an important role in computer-aided diagnosis and treatment/surgery planning. Conventional 2D convolutional neural networks (CNNs) can hardly exploit the spatial correlation of…

Image and Video Processing · Electrical Eng. & Systems 2024-05-21 Zhuoyuan Wang , Dong Sun , Xiangyun Zeng , Ruodai Wu , Yi Wang