+ equal contribution, * corresponding author
International Journal
Visibility-Aware Multi-View Stereo by Surface Normal Weighting for Occlusion Robustness
Hyucksang Lee+, Seongmin Lee+, and Sanghoon Lee*
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 9, Sep. 2025. [DB], [Project], [Code].
3D Facial Shape Similarity with Deep Perceptual Representations
Seongmin Lee+, Jiwoo Kang+, and Sanghoon Lee*
ACM Transactions on Multimedia Computing Communications and Applications, vol. 21, no. 6, Jul. 2025.
DMESH: A Structure-Preserving Diffusion Model for 3D Mesh Denoising
Seongmin Lee, Suwoong Heo, and Sanghoon Lee*
IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 3, pp. 4385-4399, Mar. 2025.
3D-PSSIM: Projective Structural Similarity for 3D Mesh Quality Assessment Robust to Topological Irregularities
Seongmin Lee, Jiwoo Kang*, Sanghoon Lee*, Weisi Lin, and Alan Conrad Bovik
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 12, pp. 9595-9611, Dec. 2024.
Stabilized Temporal 3D Face Alignment using Landmark Displacement Learning
Seongmin Lee, Hyunse Yoon, Sohyun Park, Sanghoon Lee, and Jiwoo Kang*
Electronics, vol. 12, no. 17, pp. 3735-3747, Sep. 2023.
Technical Consideration Towards Robust 3D Reconstruction with Multi-view Active Stereo Sensors
Mingyu Jang, Seongmin Lee, Jiwoo Kang*, and Sanghoon Lee*
Sensors, vol. 22, no. 11, pp. 4142-4157, May. 2022.
Competitive Learning of Facial Fitting and Synthesis using UV Energy
Jiwoo Kang, Seongmin Lee, and Sanghoon Lee*
IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 52, no. 5, pp. 2858-2873, May. 2022.
A Comparison and Evaluation of Stereo Matching on Active Stereo Images
Mingyu Jang+, Hyunse Yoon+, Seongmin Lee, Jiwoo Kang*, and Sanghoon Lee*
Sensors, vol. 22, no. 9, pp. 3332-3366, Apr. 2022.
Gradient Flow Evolution for 3D Fusion from a Single Depth Sensor
Jiwoo Kang, Seongmin Lee, Mingyu Jang, and Sanghoon Lee*
IEEE Transactions on Circuits and Systems for Video Technology, vol.32, no.4, pp. 2211-2225, Apr. 2022. [DB].
International Conference
Domain Crossover Non-Rigid Registration for 3D Human Meshes
Kyungjune Lee, Seongjean Kim, Hoseok Tong, Hyucksang Lee, Seongmin Lee*, Weisi Lin, Ping An, and Sanghoon Lee*
ACM International Conference on Multimedia (ACM MM 2025), Dublin, Ireland, 27-31 Oct. 2025.
InViTe: Individual Virtual Transfer for Personalized 3D Face Generation System
Mingyu Jang+, Kyungjune Lee+, Seongmin Lee, Hoseok Tong, Juwan Chung, Yusung Ro, and Sanghoon Lee*
International Joint Conference on Artificial Intelligence (IJCAI 2024), Demo Track, Jeju, Korea, 3-8 Aug. 2024.
AVIN-Chat: An Audio-Visual Interactive Chatbot System with Emotional State Tuning
Chanhyuk Park+, Jungbin Cho+, Junwan Kim+, Seongmin Lee, Jungsu Kim, and Sanghoon Lee*
International Joint Conference on Artificial Intelligence (IJCAI 2024), Demo Track, Jeju, Korea, 3-8 Aug. 2024.
Speech-driven Emotional 3D Talking Face Animation using Emotional Embeddings
Seongmin Lee, Jeonghaeng Lee, Hyewon Song, and Sanghoon Lee*
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024), Seoul, Korea, 14-19 Apr. 2024.
Fusing Explicit and Implicit Flow for Optical Flow Estimation
Hyunse Yoon, Seongmin Lee, and Sanghoon Lee*
IEEE International Conference on Image Processing (ICIP 2023), Kuala Lumpur, Malaysia, 8-11 Oct. 2023.
Video-based Stabilized 3D Face Alignment using Temporal Multi-Discrimination
Seongmin Lee+, Hyunse Yoon+, Jiwoo Kang, Jungsu Kim, Jiwan Son, Jungwoo Huh, and Sanghoon Lee*
IEEE Workshop on Multimedia Signal Processing (MMSP 2023), Poitiers, France, 27-29 Sep. 2023.
Video-based Face Reconstruction with Landmark Displacement Learning
Seongmin Lee+, Sohyun Park+, Hyunse Yoon, Sanghoon Lee, and Jiwoo Kang*
International Conference on Multimedia Information Technology and Applications (MITA 2023), Ostrava, Czech, 11-14 Jul. 2023. (Best Paper Award)
FaceClone: Interactive Facial Shape and Motion Cloning System using Multi-View images
Kyungjune Lee, Jeonghaeng Lee, Hyucksang Lee, Mingyu Jang, Seongmin Lee, and Sanghoon Lee*
IEEE International Conference on Multimedia and Expo Workshops (ICMEW 2023), Brisbane, Australia, 10-14 Jul. 2023.
Region Adaptive Self-Attention for an Accurate Facial Emotion Recognition
Seongmin Lee+, Jeonghaeng Lee+, Minsik Kim, and Sanghoon Lee*
Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2022), Chiang Mai, Thailand, 7-10 Nov. 2022.
Automated Pose Data Construction System for Markerless Human Motion Capture System
Uihyeon Jo, Seongmin Lee, Hyunse Yoon, Seongjean Kim, Taewan Kim, Sanghoon Lee*
International Conference on Multimedia Information Technology and Applications (MITA 2022), Jeju, Korea, 5-7 Jul. 2022.
Checkerboard Corner Localization Accelerated with Deep False Detection for Multi-camera Calibration
Jiwoo Kang, Hyunse Yoon, Seongmin Lee, and Sanghoon Lee*
Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2021), Tokyo, Japan, 14-17 Dec. 2021.
Deep Chessboard Corner Detection using Multi-task Learning
Hyunse Yoon, Seongmin Lee, Jiwoo Kang, and Sanghoon Lee*
IEEE Workshop on Multimedia Signal Processing (MMSP 2021), Tampere, Finland, 6-8 Oct. 2021.
WarpingFusion: Accurate Multi-view TSDF Fusion with Local Perspective Warp
Jiwoo Kang, Seongmin Lee, Mingyu Jang, Hyunse Yoon, and Sanghoon Lee*
IEEE International Conference on Image Processing (ICIP 2021), Anchorage, Alaska, USA, 19-22 Sep. 2021.
Active Stereo Matching Benchmark for 3D Reconstruction using Multi-view Depths
Mingyu Jang, Seongmin Lee, Jiwoo Kang, and Sanghoon Lee*
IEEE International Conference on Signal and Image Processing Applications (ICSIPA 2021), Virtual Conference, 13-15 Sep. 2021.
Sparse Checkerboard Corner Detection from Global Perspective
Jiwoo Kang, Hyunse Yoon, Seongmin Lee, and Sanghoon Lee*
IEEE International Conference on Signal and Image Processing Applications (ICSIPA 2021), Virtual Conference, 13-15 Sep. 2021. (Best Paper Award)
Image Inpainting using Weighted Mask Convolution
Jiwoo Kang, Seongmin Lee, Suwoong Heo, and Sanghoon Lee*
Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2020), Auckland, New Zealand, 7-10 Dec. 2020.
UV Completion with Self-referenced Discrimination
Jiwoo Kang+, Seongmin Lee+, and Sanghoon Lee*
Eurographics (EG 2020), Short, Norrkoping, Sweden, 25-29 May. 2020.
Physical Parameter Prediction by Embedding Human Perceptual Parameter for 3D Garment Modeling
Seongmin Lee, Woojae Kim, Sewoong Ahn, Jaekyung Kim, and Sanghoon Lee*
Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2019), Lanzhou, China, 18-21 Nov. 2019.
Dictionary-based Compression Type Classification using a CNN Architecture
Hyewon Song, Beom Kwon, Seongmin Lee, and Sanghoon Lee*
Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2019), Lanzhou, China, 18-21 Nov. 2019.
A Deep Cybersickness Predictor Based on Brain Signal Analysis for Virtual Reality Content
Jinwoo Kim, Woojae Kim, Heeseok Oh, Seongmin Lee, and Sanghoon Lee*
IEEE/CVF International Conference on Computer Vision (ICCV 2019), Seoul, Korea, 27-2 Oct.-Nov. 2019.