Publications de Kwang Moo Yi | EPFL Graph Search

Image Matching Across Wide Baselines: From Paper to Practice

Pascal Fua, Kwang Moo Yi, Eduard Trulls Fortuny, Jiri Matas, Anastasiia Mishchuk

We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task-the accuracy of the reconstructed camera pose-as our primary metric. Our pipeline's modular structure allows easy integration, confi ...

2021

Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems

Pascal Fua, Mathieu Salzmann, Zheng Dang, Kwang Moo Yi, Fei Wang, Yinlin Hu

Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be tackled by solving a linear least-square problem, which can be done by finding the eigenvector corresponding to the smal ...

IEEE COMPUTER SOC2021

Beyond Cartesian Representations for Local Descriptors

Pascal Fua, Kwang Moo Yi, Anastasiia Mishchuk, Eduard Trulls Fortuny, Patrick Winfried Josef Ebel

The dominant approach for learning local patch descriptors relies on small image regions whose scale must be properly estimated a priori by a keypoint detector. In other words, if two patches are not in correspondence, their descriptors will not match. A s ...

IEEE COMPUTER SOC2019

Learning to Find Good Correspondences

Pascal Fua, Mathieu Salzmann, Eduard Trulls Fortuny, Vincent Lepetit, Kwang Moo Yi, Yuki Ono

We develop a deep architecture to learn to find good correspondences for wide-baseline stereo. Given a set of putative sparse matches and the camera intrinsics, we train our network in an end-to-end fashion to label the correspondences as inliers or outlie ...

2018

LF-Net: Learning Local Features from Images

Pascal Fua, Kwang Moo Yi, Eduard Trulls Fortuny, Yuki Ono

We present a novel deep architecture and a training strategy to learn a local feature pipeline from scratch, using collections of images without the need for human supervision. To do so we exploit depth and relative camera pose cues to create a virtual tar ...

2018

Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses

Pascal Fua, Mathieu Salzmann, Kwang Moo Yi, Zheng Dang, Yinlin Hu, Fei Wang

Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be solved by ﬁnding the eigenvector corresponding to the smallest, or zero, eigenvalue of a matrix representing a linear sy ...

2018

Robust 3D Object Tracking from Monocular Images Using Stable Parts

Pascal Fua, Vincent Lepetit, Kwang Moo Yi, Alberto Crivellaro, Yannick Verdie, Mahdi Rad

2018

Learning to Find Good Correspondences

Pascal Fua, Mathieu Salzmann, Vincent Lepetit, Kwang Moo Yi, Eduard Trulls Fortuny, Yuki Ono

We develop a deep architecture to learn to find good correspondences for wide-baseline stereo. Given a set of putative sparse matches and the camera intrinsics, we train our network in an end-to-end fashion to label the correspondences as inliers or outlie ...

IEEE2018

Method, system, and device for learned invariant feature transform for computer images

Pascal Fua, Vincent Lepetit, Kwang Moo Yi, Eduard Trulls Fortuny

A method for training a feature detector of an image processing device, including the steps of detecting features in the image to generate a score map, computing a center of mass on the score map to generate a location, extracting a patch from the image at ...

2018

Learning Lightprobes for Mixed Reality Illumination

Pascal Fua, Vincent Lepetit, Kwang Moo Yi

This paper presents the first photometric registration pipeline for Mixed Reality based on high quality illumination estimation by convolutional neural network (CNN) methods. For easy adaptation and deployment of the system, we train the CNN using purely s ...

2017