Meta tags:
author= Hyunyoung Jung;
Headings (most frequently used words):
-
Text of the page (most frequently used words):
nbsp (12), the (8), and (8), for (7), 2021 (5), 2022 (5), hyunyoung (5), jung (5), seoul (4), computer (4), science (4), labs (4), 2023 (4), network (4), sungjoo (4), yoo (4), from (3), national (3), university (3), engineering (3), korea (3), engineer (3), intern (3), research (3), meta (3), reality (3), generative (3), aware (3), depth (3), arxiv (3), paper (3), 2019 (2), based (2), localization (2), framework (2), naver (2), software (2), jan (2), 2018 (2), feb (2), south (2), jun (2), dec (2), project (2), 2024 (2), model (2), device (2), neural (2), applications (2), images (2), any (2), information (2), radiance (2), fields (2), image (2), estimation (2), representation (2), optical (2), flow (2), resolution (2), cvpr (2), rakesh (2), ranjan (2), geometry (2), vision (2), cse (2), forked, jon, barron, website, integrated, course, bachelor, mar, 2013, aug, two, gap, years, military, service, sep, present, education, built, full, pipeline, structure, hierarchical, visual, datasets, earned, 2nd, place, both, indoor, outdoor, sections, total, prize, krw, jul, 2020, mapping, challenge, nov, qualcomm, innovation, fellowship, honors, awards, seongnam, line, plus, corp, bobidi, seattle, sunnyvale, experience, korean, government, funded, 10m, develop, automatic, optimization, methods, commercial, accelerators, development, compression, scalable, computing, edge, nerf, trained, achieve, relightability, using, only, collection, single, view, without, requiring, supplementary, reflectance, synthesis, projects, utilizes, semantic, enhance, boundary, accuracy, incorporating, metric, learning, cross, attention, code, oral, iccv, eunhyeok, park, fine, grained, semantics, enhancement, self, supervised, monocular, designed, produce, outputs, desired, while, maintaining, robust, performance, when, processing, low, highlight, denis, demandolx, feng, liu, haitao, yang, lei, luo, zhuo, hui, anyflow, arbitrary, scale, with, implicit, appearance, scene, are, coherently, stylized, guided, rgb, map, page, alexander, sorkine, hornung, nikolaos, sarafianos, seonghyeon, nam, transfer, stylizing, your, browser, does, not, support, video, tag, linkedin, google, scholar, email, core, team, working, models, mixed, obtained, under, guidance, prof, during, doctoral, studies, completed, internships, received,
Text of the page (random words):
hyunyoung jung hyunyoung jung i am a computer vision engineer on the core ai team at meta reality labs working on 3d vision and generative models for mixed reality applications i obtained my ph d in computer science and engineering cse from seoul national university under the guidance of prof sungjoo yoo during my doctoral studies i completed research internships at meta in 2022 and 2023 i received a b s in cse from seoul national university cv nbsp nbsp email nbsp nbsp google scholar nbsp nbsp linkedin research your browser does not support the video tag geometry transfer for stylizing radiance fields hyunyoung jung seonghyeon nam nikolaos sarafianos sungjoo yoo alexander sorkine hornung rakesh ranjan cvpr 2024 paper project page arxiv the geometry and appearance of a 3d scene are coherently stylized guided by an rgb image and a depth map anyflow arbitrary scale optical flow with implicit neural representation hyunyoung jung zhuo hui lei luo haitao yang feng liu sungjoo yoo rakesh ranjan denis demandolx cvpr 2023 nbsp highlight paper arxiv the optical flow network is designed to produce outputs at any desired resolution while maintaining robust performance when processing low resolution images fine grained semantics aware representation enhancement for self supervised monocular depth estimation hyunyoung jung eunhyeok park sungjoo yoo iccv 2021 nbsp oral paper arxiv code the depth estimation network utilizes semantic information to enhance boundary accuracy incorporating metric learning and cross attention projects reflectance aware generative radiance fields for 3d aware image synthesis 2021 the generative nerf based network is trained to achieve relightability using only a collection of single view images without requiring any supplementary information development of model compression framework for scalable on device ai computing on edge applications a korean government funded project 10m 2021 2024 to develop automatic dl model optimization methods for on device ai on commercial neural network accelerators experience research intern at meta reality labs jun 2023 dec 2023 nbsp sunnyvale ca us jun 2022 dec 2022 nbsp seattle wa us software engineer intern at bobidi jan 2022 feb 2022 nbsp seoul south korea software engineer intern at line plus corp jan 2018 feb 2018 nbsp seongnam south korea honors awards qualcomm innovation fellowship korea 2021 nov 2021 naver labs mapping localization challenge jul 2020 built full pipeline of structure based hierarchical visual localization framework on naver labs datasets earned 2nd place in both indoor outdoor sections total prize 6m krw education seoul national university sep 2019 present the integrated ma ph d course in computer science and engineering mar 2013 aug 2019 two gap years for military service bachelor of science in computer science and engineering forked from jon barron s website
|
