NeurIPS 2019 | R2D2: Reliable and Repeatable Detector and Descriptor
Join the channel membership:
/ aipursuit
Subscribe to the channel:
https://www.youtube.com/c/AIPursuit?s...
Support and Donation:
Paypal ⇢ https://paypal.me/tayhengee
Patreon ⇢ / hengee
BTC ⇢ bc1q2r7eymlf20576alvcmryn28tgrvxqw5r30cmpu
ETH ⇢ 0x58c4bD4244686F3b4e636EfeBD159258A5513744
Doge ⇢ DSGNbzuS1s6x81ZSbSHHV5uGDxJXePeyKy
Wanted to own BTC, ETH, or even Dogecoin? Kickstart your crypto portfolio with the largest crypto market Binance with my affiliate link:
https://accounts.binance.com/en/regis... If you enjoyed this video feel free to LIKE and SUBSCRIBE, also you can click the 🔔 for notifications!
Join this channel to get access to perks ⇢ / hengeeangus
Subscribe ⇢ https://www.youtube.com/c/HengEeAngus...
Paypal ⇢ https://paypal.me/tayhengee
Patreon ⇢ / hengee
Paper: http://papers.nips.cc/paper/9407-r2d2...
Abstract:
Interest point detection and local feature description are fundamental steps in many computer vision applications. Classical approaches are based on a detect-then-describe paradigm where separate handcrafted methods are used to first identify repeatable keypoints and then represent them with a local descriptor. Neural networks trained with metric learning losses have recently caught up with these techniques, focusing on learning repeatable saliency maps for keypoint detection or learning descriptors at the detected keypoint locations. In this work, we argue that repeatable regions are not necessarily discriminative and can therefore lead to select suboptimal keypoints. Furthermore, we claim that descriptors should be learned only in regions for which matching can be performed with high confidence. We thus propose to jointly learn keypoint detection and description together with a predictor of the local descriptor discriminativeness. This allows to avoid ambiguous areas, thus leading to reliable keypoint detection and description. Our detection-and-description approach simultaneously outputs sparse, repeatable and reliable keypoints that outperforms state-of-the-art detectors and descriptors on the HPatches dataset and on the recent Aachen Day-Night localization benchmark.