paper-with-me

홈 › Papers

gvnn: Neural Network Library for Geometric Computer Vision

2016-07-25 · Ankur Handa, Michael Bloesch, Viorica Patraucean, Simon Stent, John McCormac, Andrew Davison

We introduce gvnn, a neural network library in Torch aimed towards bridging the gap between classic geometric computer vision and deep learning. Inspired by the recent success of Spatial Transformer Networks, we propose several new layers which are often used as parametric transformations on the data in geometric computer vision. These layers can be inserted within a neural network much in the spirit of the original spatial transformers and allow backpropagation to enable end-to-end learning of a network involving any domain knowledge in geometric computer vision. This opens up applications in learning invariance to 3D geometric transformation for place recognition, end-to-end visual odometry, depth estimation and unsupervised learning through warping with a parametric transformation for image reconstruction error.

📄 PDF Abstract BibTeX arXiv:1607.07405

Code (1)

ankurhanda/gvnn 공식 구현 torch

Tasks

Image ReconstructionVisual Odometry

Methods 이 논문이 사용한 방법론

Spatial Transformer A Spatial Transformer is an image model block that explicitly allows the spatial manipulation of data within a [convolutional neural…

Similar Papers 제목 키워드 기반

Graph Variate Neural Networks

2025-09-24 · Om Roy, Yashar Moshfeghi, Keith Smith arxiv

Modelling dynamically evolving spatio-temporal signals is a prominent challenge in the Graph Neural Network (GNN) literature. Notably, GNNs assume an existing underlying graph structure. While this underlying structure m…

Graph Neural Network

AnalogVNN: A fully modular framework for modeling and optimizing photonic neural networks

2022-10-14 · Vivswan Shah, Nathan Youngblood

AnalogVNN, a simulation framework built on PyTorch which can simulate the effects of optoelectronic noise, limited precision, and signal normalization present in photonic neural network accelerators. We use this framewor…

BIG-bench Machine LearningGPUHyperparameter OptimizationManagement

ChainerCV: a Library for Deep Learning in Computer Vision

2017-08-28 · Yusuke Niitani, Toru Ogawa, Shunta Saito, Masaki Saito

Despite significant progress of deep learning in the field of computer vision, there has not been a software library that covers these methods in a unifying manner. We introduce ChainerCV, a software library that is inte…

Deep Learningobject-detectionObject DetectionSemantic Segmentation

DroneVis: Versatile Computer Vision Library for Drones

2024-06-01 · Ahmed Heakl, Fatma Youssef, Victor Parque, Walid Gomaa

This paper introduces DroneVis, a novel library designed to automate computer vision algorithms on Parrot drones. DroneVis offers a versatile set of features and provides a diverse range of computer vision tasks along wi…

Volkit: A Performance-Portable Computer Vision Library for 3D Volumetric Data

2022-03-19 · Stefan Zellmann, Giovanni Aguirre, Jürgen P. Schulze

We present volkit, an open source library with high performance implementations of image manipulation and computer vision algorithms that focus on 3D volumetric representations. Volkit implements a cross-platform, perfor…

Image Manipulation