Joo Chan Lee

I am a Ph.D. student in the department of Artificial Intelligence at Sungkyunkwan University, advised by Jong Hwan Ko and Eunbyung Park. My research interest lies in the areas of computer vision, graphics, and machine learning. Currently, I am interested in designing efficient neural fields architecture.

Email / Scholar / LinkedIn / Github

Research

Representative papers are highlighted.

	Compact 3D Gaussian Splatting for Static and Dynamic Radiance Fields Joo Chan Lee, Daniel Rho, Xiangyu Sun, Jong Hwan Ko, Eunbyung Park Preprint [Project page] [Paper] [Code] Extending the compact 3D Gaussian splatting for dynamic scene representation.
	F-3DGS: Factorized Coordinates and Representations for 3D Gaussian Splatting Xiangyu Sun, Joo Chan Lee, Daniel Rho, Jong Hwan Ko, Usman Ali, Eunbyung Park ACM MM, 2024 [Project page] [Paper] [Code] Factorized representation of 3D Gaussian Splatting, reducing storage requirements.
	Continuous Memory Representation for Anomaly Detection Joo Chan Lee, Taejune Kim, Eunbyung Park, Simon S. Woo, Jong Hwan Ko ECCV, 2024 [Project page] [Paper] [Code] A novel approach to learning normal representation in continuous feature space for anomaly detection.
	Compact 3D Gaussian Representation for Radiance Field Joo Chan Lee, Daniel Rho, Xiangyu Sun, Jong Hwan Ko, Eunbyung Park CVPR, 2024 (Highlight) [Project page] [Paper] [Code] A comprehensive framework for 3D scene representation, achieving high performance, fast training, compactness, and real-time rendering.
	Coordinate-Aware Modulation for Neural Fields Joo Chan Lee, Daniel Rho, Seungtae Nam, Jong Hwan Ko, Eunbyung Park ICLR, 2024 (Spotlight) [Project page] [Paper] [Code] Injecting spectral bias-free grid representations into the intermediate features of the MLP achieves high performance with compactness.
	FFNeRV: Flow-Guided Frame-Wise Neural Representations for Videos Joo Chan Lee, Daniel Rho, Jong Hwan Ko, Eunbyung Park ACM MM, 2023 [Project page] [Paper] [Code] Incorporating flow information into frame-wise representations to exploit the temporal redundancy across the frames in videos.
	KERNTROL: Kernel Shape Control Toward Ultimate Memory Utilization for In-Memory Convolutional Weight Mapping IEEE TCAS-I, 2024 [Paper] Kernel Shape Control for Row-Efficient Convolution on Processing-In-Memory Arrays ICCAD, 2023 [Paper] [Code] Johnny Rhe, Kang Eun Jeon, Joo Chan Lee, Seongmoon Jeong, Jong Hwan Ko A novel pruning method for a Processing-In-Memory hardware.
	Masked Wavelet Representation for Compact Neural Radiance Fields Daniel Rho, Byeonghyeon Lee, Seungtae Nam, Joo Chan Lee, Jong Hwan Ko, Eunbyung Park CVPR, 2023 [Project page] [Paper] [Code] Using the wavelet transform with learnable masking for compact grid-based neural radiance fields.
	A Reconfigurable Neural Architecture for Edge–Cloud Collaborative Real-Time Object Detection Joo Chan Lee, Yongwoo Kim, SungTae Moon, Jong Hwan Ko IEEE Internet of Things Journal, 2022 [Paper] A single-weight reconfigurable object detector for collaborative intelligence.
	Scalable Color Quantization for Task-Centric Image Compression Jae Hyun Park, Sang Hoon Kim, Joo Chan Lee, Jong Hwan Ko ACM TOMM, 2022 [Paper] Images with variable color space sizes can be extracted from a master image generated by a single DNN model.
	A Splittable DNN-Based Object Detector for Edge-Cloud Collaborative Real-Time Video Inference Joo Chan Lee, Yongwoo Kim, SungTae Moon, Jong Hwan Ko AVSS, 2021 [Paper] A splittable object detector for real-time collaborative inference.
	Robust detection of small and dense objects in images from autonomous aerial vehicles Joo Chan Lee, JeongYeop Yoo, Yongwoo Kim, SungTae Moon, Jong Hwan Ko EL, 2021 [Paper] Technical report for high performance small object detection.
	VisDrone-DET2020: The Vision Meets Drone Object Detection in Image Challenge Results Challenge Participants ECCV Workshops, 2020 [Paper] [Certificate] VisDrone Challenge 1st Place Winner.

Design and source code from Jon Barron's website.