English
Related papers

Related papers: 3D Steerable CNNs: Learning Rotationally Equivaria…

200 papers

We introduce Continual 3D Convolutional Neural Networks (Co3D CNNs), a new computational formulation of spatio-temporal 3D CNNs, in which videos are processed frame-by-frame rather than by clip. In online tasks demanding frame-wise…

Computer Vision and Pattern Recognition · Computer Science 2023-01-25 Lukas Hedegaard , Alexandros Iosifidis

With the impressive capability to capture visual content, deep convolutional neural networks (CNN) have demon- strated promising performance in various vision-based ap- plications, such as classification, recognition, and objec- t…

Computer Vision and Pattern Recognition · Computer Science 2015-09-16 Zhen Liu

This paper investigates the super-resolution (SR) of velocity fields in two-dimensional fluids from the viewpoint of rotational equivariance. SR refers to techniques that estimate high-resolution images from those in low resolution and has…

Fluid Dynamics · Physics 2022-10-26 Yuki Yasuda , Ryo Onishi

In this paper we address the problem of representing 3D visual data with parameterized volumetric shape primitives. Specifically, we present a (two-stage) approach built around convolutional neural networks (CNNs) capable of segmenting…

Computer Vision and Pattern Recognition · Computer Science 2020-01-29 Jaka Šircelj , Tim Oblak , Klemen Grm , Uroš Petković , Aleš Jaklič , Peter Peer , Vitomir Štruc , Franc Solina

Convolutional networks are successful, but they have recently been outperformed by new neural networks that are equivariant under rotations and translations. These new networks work better because they do not struggle with learning each…

Computer Vision and Pattern Recognition · Computer Science 2021-02-16 Philip Müller , Vladimir Golkov , Valentina Tomassini , Daniel Cremers

We present a PDE-based framework that generalizes Group equivariant Convolutional Neural Networks (G-CNNs). In this framework, a network layer is seen as a set of PDE-solvers where geometrically meaningful PDE-coefficients become the…

Machine Learning · Computer Science 2022-08-24 Bart Smets , Jim Portegies , Erik Bekkers , Remco Duits

Defining and reliably finding a canonical orientation for 3D surfaces is key to many Computer Vision and Robotics applications. This task is commonly addressed by handcrafted algorithms exploiting geometric cues deemed as distinctive and…

Computer Vision and Pattern Recognition · Computer Science 2020-11-16 Riccardo Spezialetti , Federico Stella , Marlon Marcon , Luciano Silva , Samuele Salti , Luigi Di Stefano

We propose a spherical kernel for efficient graph convolution of 3D point clouds. Our metric-based kernels systematically quantize the local 3D space to identify distinctive geometric relationships in the data. Similar to the regular grid…

Computer Vision and Pattern Recognition · Computer Science 2020-03-24 Huan Lei , Naveed Akhtar , Ajmal Mian

The usage of 3D vision algorithms, such as shape reconstruction, remains limited because they require inputs to be at a fixed canonical rotation. Recently, a simple equivariant network, Vector Neuron (VN) has been proposed that can be…

Computer Vision and Pattern Recognition · Computer Science 2024-05-09 Dongwon Son , Jaehyung Kim , Sanghyeon Son , Beomjoon Kim

The translational equivariant nature of Convolutional Neural Networks (CNNs) is a reason for its great success in computer vision. However, networks do not enjoy more general equivariance properties such as rotation or scaling, ultimately…

Computer Vision and Pattern Recognition · Computer Science 2023-03-02 Zikai Sun , Thierry Blu

3D action recognition was shown to benefit from a covariance representation of the input data (joint 3D positions). A kernel machine feed with such feature is an effective paradigm for 3D action recognition, yielding state-of-the-art…

Computer Vision and Pattern Recognition · Computer Science 2017-10-05 Jacopo Cavazza , Pietro Morerio , Vittorio Murino

In many computer vision tasks, we expect a particular behavior of the output with respect to rotations of the input image. If this relationship is explicitly encoded, instead of treated as any other variation, the complexity of the problem…

Computer Vision and Pattern Recognition · Computer Science 2018-07-06 Diego Marcos , Michele Volpi , Nikos Komodakis , Devis Tuia

Group equivariant convolutional networks (GCNNs) endow classical convolutional networks with additional symmetry priors, which can lead to a considerably improved performance. Recent advances in the theoretical description of GCNNs revealed…

Machine Learning · Computer Science 2021-01-22 Leon Lang , Maurice Weiler

Large kernel convolutions offer a scalable alternative to vision transformers for high-resolution 3D volumetric analysis, yet naively increasing kernel size often leads to optimization instability. Motivated by the spatial bias inherent in…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Ho Hin Lee , Quan Liu , Shunxing Bao , Yuankai Huo , Bennett A. Landman

At this work we introduce horizontally symmetric convolutional kernels for CNNs which make the network output invariant to horizontal flips of the image. We also study other types of symmetric kernels which lead to vertical flip invariance,…

Computer Vision and Pattern Recognition · Computer Science 2018-05-25 Viacheslav Dudar , Vladimir Semenov

We present first empirical results from our ongoing investigation of distribution shifts in image data used for various computer vision tasks. Instead of analyzing the original training and test data, we propose to study shifts in the…

Computer Vision and Pattern Recognition · Computer Science 2022-01-24 Paul Gavrikov , Janis Keuper

Surface meshes are widely used shape representations and capture finer geometry data than point clouds or volumetric grids, but are challenging to apply CNNs directly due to their non-Euclidean structure. We use parallel frames on surface…

Computer Vision and Pattern Recognition · Computer Science 2020-06-15 Yuqi Yang , Shilin Liu , Hao Pan , Yang Liu , Xin Tong

We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold: 1) 3D ConvNets are…

Computer Vision and Pattern Recognition · Computer Science 2015-10-08 Du Tran , Lubomir Bourdev , Rob Fergus , Lorenzo Torresani , Manohar Paluri

Many problems across computer vision and the natural sciences require the analysis of spherical data, for which representations may be learned efficiently by encoding equivariance to rotational symmetries. We present a generalized spherical…

Computer Vision and Pattern Recognition · Computer Science 2021-03-09 Oliver J. Cobb , Christopher G. R. Wallis , Augustine N. Mavor-Parker , Augustin Marignier , Matthew A. Price , Mayeul d'Avezac , Jason D. McEwen

We propose a new model for digital pathology segmentation, based on the observation that histopathology images are inherently symmetric under rotation and reflection. Utilizing recent findings on rotation equivariant CNNs, the proposed…

Computer Vision and Pattern Recognition · Computer Science 2018-06-12 Bastiaan S. Veeling , Jasper Linmans , Jim Winkens , Taco Cohen , Max Welling