Transforming realistic photos into cartoon style images!๐Ÿ˜…
https://www.profillic.com/paper/arxiv:1911.06102

(Cartoonization is achieved by conducting some transformation manipulation in the feature space with their proposed Soft-AdaIN)
https://www.facebook.com/groups/DeepNetGroup/permalink/1004183859974496/?sfnsn=mo

'Deep Learning > Papers2read' ์นดํ…Œ๊ณ ๋ฆฌ์˜ ๋‹ค๋ฅธ ๊ธ€

TensorFlow Korea ๋…ผ๋ฌธ์ฝ๊ธฐ๋ชจ์ž„ PR12 207๋ฒˆ์งธ ๋…ผ๋ฌธ review์ž…๋‹ˆ๋‹ค ์ด๋ฒˆ ๋…ผ๋ฌธ์€ YOLO v3์ž…๋‹ˆ๋‹ค. ๋งค์šฐ ์œ ๋ช…ํ•œ ๋…ผ๋ฌธ์ด๋ผ์„œ ํฌ๊ฒŒ ๋ถ€์—ฐ์„ค๋ช…์ด ํ•„์š”์—†์„ ๊ฒƒ ๊ฐ™์€๋ฐ์š”, Object Detection algorithm๋“ค ์ค‘์— YOLO๋Š” ๊ต‰์žฅํžˆ..  (0) 2019.11.18
์•ˆ๋…•ํ•˜์„ธ์š”, ์ˆ˜์•„๋žฉ(์ฝ”๊ทธ๋„ฅ์Šค)์˜ ์ดํ˜ธ์„ฑ์ด๋ผ๊ณ  ํ•ฉ๋‹ˆ๋‹ค. ์ด๋ฒˆ์— PR12 ๋ชจ์ž„์— ํ•ฉ๋ฅ˜ํ•˜๊ฒŒ ๋˜๋ฉด์„œ ์ฒซ ๋ฐœํ‘œ๋ฅผ ํ•˜๊ฒŒ ๋˜์—ˆ์Šต๋‹ˆ๋‹ค! ์ €๋Š” 208๋ฒˆ์งธ ๋…ผ๋ฌธ ๋ฆฌ๋ทฐ๋ฅผ ์ง„ํ–‰ํ•˜๊ฒŒ ๋˜์—ˆ๊ณ , ๋ฐœํ‘œ ์ฃผ์ œ๋Š” "Unsupervised vis..  (0) 2019.11.18
From ICDAR 2019: Face Detection in camera-captured images of identity documents under challenging conditions https://www.profillic.com/paper/arxiv:1911.03567 (They survey three state-of-the-art face detection methods based on general images, i.e. Casc..  (0) 2019.11.13
ImageNet Classification์—์„œ State-of-the-art(SOTA)๋ฅผ ๋˜! ๊ฐฑ์‹ ํ•œ ๋…ผ๋ฌธ์ด ์ดํ‹€์ „ ๊ณต๊ฐœ๊ฐ€ ๋˜์—ˆ์Šต๋‹ˆ๋‹ค. ๋…ผ๋ฌธ ์ œ๋ชฉ: Self-training with Noisy Student improves ImageNet classification [๋…ผ๋ฌธ ๋งํฌ: https://arxiv.org/pdf/1911.04252...  (0) 2019.11.13
TF-KR PR-12 206๋ฒˆ์งธ ๋ฐœํ‘œ๋Š” PointRCNN ์ด๋ผ๋Š” ๋…ผ๋ฌธ์ž…๋‹ˆ๋‹ค. raw point cloud์—์„œ 3์ฐจ์› ๋ฌผ์ฒด์˜ bounding box๋ฅผ ์ฐพ๋Š” ์—ฐ๊ตฌ์ž…๋‹ˆ๋‹ค. PR-12์—์„œ point cloud์™€ ๊ด€๋ จ๋œ ๋ฐœํ‘œ๋Š” ์ฒ˜์Œ์ด์—ˆ๋Š”๋ฐ, ์ € ๋˜ํ•œ ์ด ๋ถ„์•ผ์— ๋Œ€ํ•ด ..  (0) 2019.11.12
Posted by uniqueone
,