In-Jae Lee

I am a second-year Ph.D. candidate supervised by Jaesik Park at the Visual & Geometric Intelligence Lab in SNU.

Before starting my Ph.D., I obtained a mastser's degree from Graduate School of Mobility at KAIST, where I was a memeber of AXE Lab. Before that, I earned a bachelor's degree in Automotive Engineering from the KMU.

Email / CV / Google Scholar / Github / Linkedin

News

[2025.09]	Our OpenBox, an automatic annotation pipeline for 3D bounding box, is accepted to NeurIPS 2025 as a spotlight!
[2025.01]	Our CRAB, a camera-radar fusion for 3D peception is accepted to ICRA 2025!

Research

I am interested in 3D computer vision, especially 3D perception and scene understanding for robot vision. My research focuses on multi-modal sensor fusion, including camera, LiDAR, and radar, to enhance the perception capabilities of autonomous systems. I am also passionate about leveraging visual foundation model for 3D perception.

	SpatialMosaic: A Multiview VLM Dataset for Partial Visibility Kanghee Lee, In-Jae Lee, Minseok Kwak, Kwonyoung Ryu, Jungi Hong and Jaesik Park Under Review paper
	OpenBox: Annotate Any 3D Bounding Boxes In-Jae Lee, Moongyeom Kim, Kwonyoung Ryu, Pierre Musacchio and Jaesik Park NeurIPS 2025 (Spotlight) paper \| video \| project page
	CRAB: Camera-Radar Fusion for Reducing Depth Ambiguity in Backward Projection based View Transformation In-Jae Lee, Sihwan Hwang, Youngseok Kim, Wonjune Kim, Sanmin Kim and Dongsuk Kum ICRA 2025 paper
	Predict to Detect: Prediction-guided 3D Object Detection using Sequential Images Sanmin Kim, Youngseok Kim, In-Jae Lee and Dongsuk Kum ICCV 2023 paper \| code
	CRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perception Youngseok Kim, Juyeb shin, Sanmin Kim, In-Jae Lee, Jun Won Choi and Dongsuk Kum ICCV 2023 paper \| video \| code

This website's source code is from Jon Barron.