AI Learns Geometric Descriptors From Depth Images | Two Minute Papers #148

3:07

AI Learns Geometric Descriptors From Depth Images | Two Minute Papers #148

Two Minute Papers 27.04.2017 13 385 просмотров 553 лайков

Machine-readable: Markdown · JSON API · Site index

Смотреть на YouTube

Поделиться Telegram VK Бот

Транскрипт Скачать .md

Анализ с AI

Описание видео

The paper "3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions" is available here: http://3dmatch.cs.princeton.edu/ Recommended for you: Our earlier episode on Siamese networks - https://www.youtube.com/watch?v=a3sgFQjEfp4 WE WOULD LIKE TO THANK OUR GENEROUS PATREON SUPPORTERS WHO MAKE TWO MINUTE PAPERS POSSIBLE: Andrew Melnychuk, Christian Lawson, Daniel John Benton, Dave Rushton-Smith, Esa Turkulainen, Sunil Kim, VR Wizard. https://www.patreon.com/TwoMinutePapers Awesome Two Minute Papers merch: http://twominutepapers.com/ Music: Antarctica by Audionautix is licensed under a Creative Commons Attribution license (https://creativecommons.org/licenses/by/4.0/) Artist: http://audionautix.com/ Thumbnail background image credit: https://pixabay.com/photo-1851258/ Splash screen/thumbnail design: Felícia Fehér - http://felicia.hu Károly Zsolnai-Fehér's links: Facebook → https://www.facebook.com/TwoMinutePapers/ Twitter → https://twitter.com/karoly_zsolnai Web → https://cg.tuwien.ac.at/~zsolnai/

Оглавление (6 сегментов)

<Untitled Chapter 1>

dear fellow Scholars this is 2minute papers with carool today we are going to discuss a great piece of work that shows us how efficient and versatile neural network-based techniques had become recently here the input is a bunch of rgbd images which are photographs endowed with depth information and the output can be a full 3d reconstruction of a scene and much more which we'll see in a moment this task is typically taken care of by handcrafting descript a descriptor is a specialized

Hand-Crafted 3D Local Descriptors

representation for doing useful tasks on images and other data structures for instance if we seek to build an algorithm to recognize black and white images a useful descriptor would definitely contain the number of colors that are visible in an image and a list of these colors again these descriptors

Learning from RGB-D Reconstructions

have been typically handcrafted by scientists for decades new problem new descriptors new papers but not this time because here super effective descript scriptors are proposed automatically via a learning algorithm a convolutional neural network and Siamese networks this is incredible creating such descriptors took extremely smart researchers and years of work on a specific problem and were still often not as good as these ones by the way we have discussed Siamese networks in an earlier episode as always the link is available in the video description and as you can imagine several really cool applications emerg from this one when combined with ransac

3D Reconstruction

a technique used to find order in noisy measurement data it is able to perform 3D scene Reconstruction from just a few images and it completely smokes the competition two post estimation with

6D Object Pose Estimation

bounding boxes given a sample of an object the algorithm is able to recognize not only the shape itself but also its orientation when given a scene cluttered with other objects three correspondence search is possible

Mesh Correspondences

this is really cool this means that a semantically similar piece of geometry is recognized on different objects for instance the algorithm can learn the concept of a handle and recognize the handles on a variety of objects such as on motorcycles carriages chairs and more the source code of this project is also available YooHoo neural networks are rapidly establishing Supremacy in a number of research fields and I am so happy to be alive in this age of incredible research progress make sure to subscribe to the series and click the Bell icon some amazing works are coming up in the next few episodes and there will be lots of fun to be had thanks for watching and for your generous support and I'll see you next time oh

Другие видео автора — Two Minute Papers

Ctrl+V

Экстракт Знаний в Telegram

Экстракты и дистилляты из лучших YouTube-каналов — сразу после публикации.

Подписаться

Лучшие методички за неделю — каждый понедельник