Jinyeong Chae
I'm an AI engineer at SK Broadband in Seoul.
My research interest lies in the areas of artificial intelligence, computer vision, and knowledge-based reasoning. Specifically, I am interested in how to perceive rich information from the world with limited or multimodal data.
Previously, I was at Visual Information Processing Lab , Seoul National University advised by Prof. Joonseok Lee , studying computer vision.
Before that, I received a Master's degree in Artificial Intelligence at Dongguk University(DGU) and Bachelor's degrees in Statistics and Software Convergence at DGU, where I worked with Prof. Jihie Kim .
Email /
Scholar /
Linkedin /
Github
Towards a Complete Benchmark on Video Moment Localization
Jinyeong Chae ,
Donghwa Kim ,
Kwanseok Kim ,
Doyeon Lee ,
Sangho Lee ,
Seongsu Ha ,
Jonghwan Mun ,
Wooyoung Kang ,
Byungseok Roh ,
Joonseok Lee
Artificial Intelligence and Statistics (AISTATS) , 2024
Code
conduct an extensive benchmark study to measure the performance of representative methods on moment localization task.
Your browser does not support the video tag.
Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation
Hadi Alzayer ,
Philipp Henzler ,
Jonathan T. Barron ,
Jia-Bin Huang ,
Pratul P. Srinivasan ,
Dor Verbin
arXiv , 2024
project page
/
arXiv
Images taken under extreme illumination variation can be made consistent with diffusion, and this enables high-quality 3D reconstruction.
Your browser does not support the video tag.
SimVS: Simulating World Inconsistencies for Robust View Synthesis
Alex Trevithick ,
Roni Paiss ,
Philipp Henzler ,
Dor Verbin ,
Rundi Wu ,
Hadi Alzayer ,
Ruiqi Gao ,
Ben Poole ,
Jonathan T. Barron ,
Aleksander Holynski ,
Ravi Ramamoorthi ,
Pratul P. Srinivasan
arXiv , 2024
project page
/
arXiv
Simulating the world with video models lets you make inconsistent captures consistent.
Your browser does not support the video tag.
CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models
Rundi Wu ,
Ruiqi Gao ,
Ben Poole ,
Alex Trevithick ,
Changxi Zheng ,
Jonathan T. Barron ,
Aleksander Holynski
arXiv , 2024
project page
/
arXiv
An approach for turning a video into a 4D radiance field that can be rendered in real-time. When combined with a text-to-video model, this enables text-to-4D.
EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis
Alexander Mai ,
Peter Hedman ,
George Kopanas ,
Dor Verbin ,
David Futschik ,
Qiangeng Xu ,
Falko Kuester ,
Jonathan T. Barron ,
Yinda Zhang
arXiv , 2024
project page
/
arXiv
Raytracing constant-density ellipsoids yields more accurate and flexible radiance fields than splatting Gaussians, and still runs in real-time.
Your browser does not support the video tag.
CAT3D: Create Anything in 3D with Multi-View Diffusion Models
Ruiqi Gao *,
Aleksander Holynski *,
Philipp Henzler ,
Arthur Brussee ,
Ricardo Martin Brualla ,
Pratul P. Srinivasan ,
Jonathan T. Barron ,
Ben Poole *
NeurIPS , 2024 (Oral Presentation) project page
/
arXiv
A single model built around diffusion and NeRF that does text-to-3D, image-to-3D, and few-view reconstruction, trains in 1 minute, and renders at 60FPS in a browser.
Micropapers
Squareplus: A Softplus-Like Algebraic Rectifier
A Convenient Generalization of Schlick's Bias and Gain Functions
Continuously Differentiable Exponential Linear Units
Scholars & Big Models: How Can Academics Adapt?
Recorded Talks
View Dependent Podcast, 2024
Bay Area Robotics Symposium, 2023
EGSR Keynote, 2021
TUM AI Lecture Series, 2020
Vision & Graphics Seminar at MIT, 2020
Academic Service
Area Chair, CVPR 2025
Area Chair, CVPR 2024
Demo Chair, CVPR 2023
Area Chair, CVPR 2022
Area Chair & Award Committee Member, CVPR 2021
Area Chair, CVPR 2019
Area Chair, CVPR 2018
Teaching
Graduate Student Instructor, CS188 Spring 2011
Graduate Student Instructor, CS188 Fall 2010
Figures, "Artificial Intelligence: A Modern Approach", 3rd Edition
Feel free to steal this website's source code . Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman 's Jekyll fork of this page.
