Jaesung Choe

Hi, I am a research scientist at NVIDIA Research Taiwan. My main research interest is 3D vision language models from 3D pointclouds, 3D Gaussians, and 3D humans.

I received my PhD from KAIST under the supervision of In So Kweon. I finished my research internship at NVIDIA Research with Christopher Choy, Anima Anandkumar, and at Meta with Shuochen Su.

Résumé / jchoe _at_ nvidia _dot_ com / Google Scholar / LinkedIn

News

If you're interested in a 2025 internship, please (1) send me an email, and submit your application at (2) NVIDIA career.

Research

I'm interested in computer vision for 3D scene understanding, such as (1) 3D Visual Language Model, (2) 3D Scene Reconstruction and Neural Rendering and (3) 3D Vehicle/Object Perception. Some papers are highlighted.

	Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering Cheng Sun, Jaesung Choe, Charles Loop, Wei-Chiu Ma, Yu-Chiang Frank Wang arXiv, 2024 [Paper] Extend to use the rasterization technique into the sparse voxel representation for the image rendering task.
	Spacetime Surface Regularization for Neural Dynamic Scene Reconstruction Jaesung Choe, Christopher Choy, Jaesik Park, In So Kweon, Anima Anandkumar ICCV, 2023 [Paper] Apply spacetime surface regularization technique for 4D surface reconstruction and dynamic scene rendering.
	PointMixer: MLP-Mixer for Point Cloud Understanding Jaesung Choe, Chunghyun Park, Francois Rameau, Jaesik Park, In So Kweon ECCV, 2022 [Paper] [Code] [Poster] [Video] Design a new MLP-only architecture for 3D points. Introduced by AK.
	Deep Point Cloud Reconstruction Jaesung Choe, ByeongIn Joung, Francois Rameau, Jaesik Park, In So Kweon ICLR, 2022 [Paper] Perform the point cloud upsampling and denoising tasks simultaneously. Demonstrate good generalization performance.
	VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction Jaesung Choe, Sunghoon Im, Francois Rameau, Minjun Kang, In So Kweon ICCV, 2021 [Paper] [Video] [Slide] Propose deep learning based depth fusion algorithm for indoor scene reconstruction.
	Volumetric Propagation Network: Stereo-LiDAR Fusion for Long-Range Depth Estimation Jaesung Choe, Kyungdon Joo, Tooba Imtiaz, In So Kweon RA-L, 2021 [Paper (RA-L)] [Paper (ICRA)] [Video] Estimation dense depth maps by fusing LiDAR points and stereo images.

Mentorship

Yoonwoo Jeong (research intern - 2024)
Chunghyun Park (research intern - 2023)

Academic collaboration

Ji-Yeon Kim (POSTECH - 2024)
Jun-Seong Kim (POSTECH - 2024)
Minjun Kang (KAIST - 2023)

Talks

Pusan Univ., Sep 2024
Hangyang Univ., Sep 2024
DGIST, April 2024
Kakao Brain, May 2022

Source code for this page was taken from Jon Barron's website.