Precisely estimating a robot’s pose in a prior, global map is a challenge in unstructured, dynamic environments.https://www.profillic.com/paper/arxiv:1909.12837Solution: SegMap: a map representation solution for localization and mapping

Deep Learning/Papers2read 2019. 10. 2. 13:35

Precisely estimating a robot’s pose in a prior, global map is a challenge in unstructured, dynamic environments.

Solution: SegMap: a map representation solution for localization and mapping

Modern problems require modern solutions: Protecting privacy using deepfakes https://www.profillic.com/paper/arxiv:1909.04538 (0)	2019.10.04
Built by Stanford researchers: TunaGAN: Modify high-resolution face images with good qualitative and quantitative performance.https://www.profillic.com/paper/arxiv:1908.06163 (0)	2019.10.02
Great applications for the fashion industry-Poly-GAN: Garments are automatically placed on images of human models at an arbitrary posehttps://www.profillic.com/paper/arxiv:1909.02165 (0)	2019.10.02
안녕하세요, 수아랩의 이호성입니다.얼마전에 ICCV 2019 학회에 대한 간단한 시각화 자료를 공유드렸었는데요, 이번에는 제 관심사를 바탕으로 1077편의 논문 중에 22편을 정해서 각 논문당 2~3줄.. (0)	2019.10.01
이번 스터디에서는 BNN 학습을 Cost Function을 정의하고 최적화하여 접근하는 방식을 소개한 XNOR-Net과 1x1 Conv와 3x3 Conv의 조합을 통해 Network를 Reduction하는 SqueezeNet을 다루었습니다! 두 발표자분 모.. (0)	2019.10.01