Search Results for author: Daniel DeTone

Found 7 papers, 3 papers with code

ODAM: Object Detection, Association, and Mapping using Posed RGB Video

no code implementations23 Aug 2021 Kejie Li, Daniel DeTone, Steven Chen, Minh Vo, Ian Reid, Hamid Rezatofighi, Chris Sweeney, Julian Straub, Richard Newcombe

Localizing objects and estimating their extent in 3D is an important step towards high-level 3D scene understanding, which has many applications in Augmented Reality and Robotics.

3D Object Detection Scene Understanding

SuperGlue: Learning Feature Matching with Graph Neural Networks

13 code implementations CVPR 2020 Paul-Edouard Sarlin, Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich

This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points.

Pose Estimation Visual Place Recognition

Self-Improving Visual Odometry

no code implementations8 Dec 2018 Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich

We propose a self-supervised learning framework that uses unlabeled monocular video sequences to generate large-scale supervision for training a Visual Odometry (VO) frontend, a network which computes pointwise data associations across images.

Pose Estimation Self-Supervised Learning +1

Deep ChArUco: Dark ChArUco Marker Pose Estimation

no code implementations CVPR 2019 Danying Hu, Daniel DeTone, Vikram Chauhan, Igor Spivak, Tomasz Malisiewicz

We evaluate Deep ChArUco in challenging low-light, high-motion, high-blur scenarios and demonstrate that our approach is superior to a traditional OpenCV-based method for ChArUco marker detection and pose estimation.

Data Augmentation Pose Estimation

SuperPoint: Self-Supervised Interest Point Detection and Description

17 code implementations20 Dec 2017 Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich

This paper presents a self-supervised framework for training interest point detectors and descriptors suitable for a large number of multiple-view geometry problems in computer vision.

Domain Adaptation Homography Estimation

Toward Geometric Deep SLAM

no code implementations24 Jul 2017 Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich

The first network, MagicPoint, operates on single images and extracts salient 2D points.

Deep Image Homography Estimation

8 code implementations13 Jun 2016 Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich

We present a deep convolutional neural network for estimating the relative homography between a pair of images.

Homography Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.