Author name cluster

Sanghoon Lee

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

11 papers

1 author row

AAAI Conference 2026 Conference Paper

DipGuava: Disentangling Personalized Gaussian Features for 3D Head Avatars from Monocular Video

Jeonghaeng Lee
Seok Keun Choi
Zhixuan Li
Weisi Lin
Sanghoon Lee

While recent 3D head avatar creation methods attempt to animate facial dynamics, they often fail to capture personalized details, limiting realism and expressiveness. To fill this gap, we present DipGuava (Disentangled and Personalized Gaussian UV Avatar), a novel 3D Gaussian head avatar creation method that successfully generates avatars with personalized attributes from monocular video. DipGuava is the first method to explicitly disentangle facial appearance into two complementary components, trained in a structured two-stage pipeline that significantly reduces learning ambiguity and enhances reconstruction fidelity. In the first stage, we learn a stable geometry-driven base appearance that captures global facial structure and coarse expression-dependent variations. In the second stage, the personalized residual details not captured in the first stage are predicted, including high-frequency components and nonlinearly varying features such as wrinkles and subtle skin deformations. These components are fused via dynamic appearance fusion that integrates residual details after deformation, ensuring spatial and semantic alignment. This disentangled design enables DipGuava to generate photorealistic, identity-preserving avatars, consistently outperforming prior methods in both visual quality and quantitative performance, as demonstrated in extensive experiments.

PDF Details DOI

TIST Journal 2025 Journal Article

A Novel Intelligent Video Surveillance System Using Low-Traffic Scene-Preserving Video Anonymization

Jungwoo Huh
Jiwoo Kang
Jongwook Woo
Sanghoon Lee

With the development of computer vision technology, intelligent video surveillance systems have been developed for automatic monitoring. However, the problem of personal information protection has also emerged. Existing systems attempted to solve this problem by anonymizing a video by, for example, sending only low-dimensional abstract information such as a person’s 2D pose or blurring a person’s face in the video before sending it to the central cloud server. However, these approaches failed to balance scene-preservation and traffic efficiency, because abstract information is too limited for preserving the entire scene, and video modification generates massive traffic. This article proposes a novel intelligent video surveillance system to overcome such limitations that preserves the scene information and generates minimal traffic through video anonymization. The proposed system reconstructs 3D human models and estimates segmentation masks to preserve a scene captured by a surveillance camera in its entirety. Parametric models represent 3D human models with several sets of parameters, and dictionary coding compresses the segmentation mask with a high compression ratio. The system follows the edge-cloud architecture, where the edge node extracts and transmits the scene information and the central cloud server generates the final anonymized video. We demonstrate the effectiveness of the proposed system by conducting experiments on processing time, scene preservation, and traffic efficiency. Our proposed system runs in real-time ( $>$ 25fps) in a typical hardware setting and has a data compression ratio of more than 5,000 compared with raw data transfer while maintaining over 85% scene-preservation correlation with the original video.

Details DOI

AAAI Conference 2025 System Paper

SDAS: Semantic Data Acquisition System for Minimizing Redundancy and Maximizing Diversity

Yeseung Park
Hyunse Yoon
Jungwoo Huh
Jungsu Kim
Jeongwook Choi
Sanghoon Lee

In this paper, we propose SDAS, a new motion data assessment and storage system designed to acquire new motion data with reduced redundancy and maximizing diversity. SDAS collects data in the field, retrieves the most similar data from the database in real-time, and provides visualization tools that allow for the comparison of differences between the capture data and the stored data. Through this system, researchers can efficiently build and manage a database. The demonstration video is available at https://youtu.be/vqW0uMDnZTw.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

AVIN-Chat: An Audio-Visual Interactive Chatbot System with Emotional State Tuning

Chanhyuk Park
Jungbin Cho
Junwan Kim
Seongmin Lee
Jungsu Kim
Sanghoon Lee

This work presents an audio-visual interactive chatbot (AVIN-Chat) system that allows users to have face-to-face conversations with 3D avatars in real-time. Compared to the previous chatbot services, which provide text-only or speech-only communications, the proposed AVIN-Chat can offer audio-visual communications providing users with a superior experience quality. In addition, the proposed AVIN-Chat emotionally speaks and expresses according to the user's emotional state. Thus, it enables users to establish a strong bond with the chatbot system, increasing the user's immersion. Through user subjective tests, it is demonstrated that the proposed system provides users with a higher sense of immersion than previous chatbot systems. The demonstration video is available at https: //www. youtube. com/watch? v=Z74uIV9k7_k.

PDF Details DOI

EAAI Journal 2024 Journal Article

Double reverse diffusion for realistic garment reconstruction from images

Jeonghaeng Lee
Duc Nguyen
Jongyoo Kim
Jiwoo Kang
Sanghoon Lee

Creating realistic digital 3D avatars has been getting more attention thanks to the introduction of new multimedia formats such as augmented and virtual reality. An important factor making avatars realistic is clothes. In this paper, we investigate a new method to reconstruct realistic garments from a set of images and body information. Early methods working on realistic images struggle to faithfully reconstruct the garment details. As deep learning is increasingly applied to geometric data which can conveniently represent garments, we devise a novel deep learning-based solution to the garment reconstruction problem. We offer a new perspective on the reconstruction problem and treat it as a reversion of the smoothing diffusion process. To achieve this goal, we propose to deform the smoothed human mesh into a clothed human via a Double Reverse Diffusion (DReD) process. For the first reverse diffusion, we introduce a novel operator called Graph Long Short-Term Memory (GraphLSTM) which recursively diffuses features to produce a deformed mesh by modeling the relationships between vertices. Then, the output mesh can be repeatedly upsampled and deformed by the above pipeline to obtain finer garment details, which can be seen as another reverse diffusion process. To obtain features for the reverse diffusion, we extract pixel-aligned features transferred from images and explore to incorporate the visibility of garments from the image viewpoints. Through detailed experiments on two public datasets, we demonstrate that DReD synthesizes more realistic wrinkled garments with lower errors and offers faster inference than previous methods.

Details DOI

IJCAI Conference 2024 Conference Paper

InViTe: Individual Virtual Transfer for Personalized 3D Face Generation System

Mingyu Jang
Kyungjune Lee
Seongmin Lee
Hoseok Tong
Juwan Chung
Yusung Ro
Sanghoon Lee

With the expansion of the virtual communication industry using VR/AR, it has attracted increasing attention to enable users to represent their personalities in a 3D avatar. As the face of 3D avatars plays a crucial role in conveying human personality, a system that generates and manipulates 3D faces is desired. However, establishing the system is challenging due to the need for human effort and specialized knowledge. To fill this void, we present the Individual Virtual Transfer (InViTe), which enables the creation and customization of a 3D face according to the user's preference. Our proposed system is featured for 1) 3D face reconstruction with high fidelity texture map, 2) 3D face personalization, 3) realistic rendering results, and 4) real-time mobile virtual applications. We conduct an experiment to demonstrate that the proposed system can achieve sufficient individual personalization of 3D faces. Furthermore, we evaluate the system's data transmission protocol and demonstrate its efficiency. The demonstration video is available at https: //www. youtube. com/watch? v=D 4pXZvGUWU.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

TurboHopp: Accelerated Molecule Scaffold Hopping with Consistency Models

Kiwoong Yoo
Owen Oertell
Junhyun Lee
Sanghoon Lee
Jaewoo Kang

Navigating the vast chemical space of druggable compounds is a formidable challenge in drug discovery, where generative models are increasingly employed to identify viable candidates. Conditional 3D structure-based drug design (3D-SBDD) models, which take into account complex three-dimensional interactions and molecular geometries, are particularly promising. Scaffold hopping is an efficient strategy that facilitates the identification of similar active compounds by strategically modifying the core structure of molecules, effectively narrowing the wide chemical space and enhancing the discovery of drug-like products. However, the practical application of 3D-SBDD generative models is hampered by their slow processing speeds. To address this bottleneck, we introduce TurboHopp, an accelerated pocket-conditioned 3D scaffold hopping model that merges the strategic effectiveness of traditional scaffold hopping with rapid generation capabilities of consistency models. This synergy not only enhances efficiency but also significantly boosts generation speeds, achieving up to 30 times faster inference speed as well as superior generation quality compared to existing diffusion-based models, establishing TurboHopp as a powerful tool in drug discovery. Supported by faster inference speed, we further optimize our model, using Reinforcement Learning for Consistency Models (RLCM), to output desirable molecules. We demonstrate the broad applicability of TurboHopp across multiple drug discovery scenarios, underscoring its potential in diverse molecular settings. The code is provided at https: //github. com/orgw/TurboHopp

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation

Donghyeon Baek
Youngmin Oh
Sanghoon Lee
Junghyup Lee
Bumsub Ham

Class-incremental semantic segmentation (CISS) labels each pixel of an image with a corresponding object/stuff class continually. To this end, it is crucial to learn novel classes incrementally without forgetting previously learned knowledge. Current CISS methods typically use a knowledge distillation (KD) technique for preserving classifier logits, or freeze a feature extractor, to avoid the forgetting problem. The strong constraints, however, prevent learning discriminative features for novel classes. We introduce a CISS framework that alleviates the forgetting problem and facilitates learning novel classes effectively. We have found that a logit can be decomposed into two terms. They quantify how likely an input belongs to a particular class or not, providing a clue for a reasoning process of a model. The KD technique, in this context, preserves the sum of two terms ($\textit{i. e. }$, a class logit), suggesting that each could be changed and thus the KD does not imitate the reasoning process. To impose constraints on each term explicitly, we propose a new decomposed knowledge distillation (DKD) technique, improving the rigidity of a model and addressing the forgetting problem more effectively. We also introduce a novel initialization method to train new classifiers for novel classes. In CISS, the number of negative training samples for novel classes is not sufficient to discriminate old classes. To mitigate this, we propose to transfer knowledge of negatives to the classifiers successively using an auxiliary classifier, boosting the performance significantly. Experimental results on standard CISS benchmarks demonstrate the effectiveness of our framework.

PDF Details

AIIM Journal 2017 Journal Article

An algorithm for direct causal learning of influences on patient outcomes

Chandramouli Rathnam
Sanghoon Lee
Xia Jiang

Objective This study aims at developing and introducing a new algorithm, called direct causal learner (DCL), for learning the direct causal influences of a single target. We applied it to both simulated and real clinical and genome wide association study (GWAS) datasets and compared its performance to classic causal learning algorithms. Method The DCL algorithm learns the causes of a single target from passive data using Bayesian-scoring, instead of using independence checks, and a novel deletion algorithm. We generate 14, 400 simulated datasets and measure the number of datasets for which DCL correctly and partially predicts the direct causes. We then compare its performance with the constraint-based path consistency (PC) and conservative PC (CPC) algorithms, the Bayesian-score based fast greedy search (FGS) algorithm, and the partial ancestral graphs algorithm fast causal inference (FCI). In addition, we extend our comparison of all five algorithms to both a real GWAS dataset and real breast cancer datasets over various time-points in order to observe how effective they are at predicting the causal influences of Alzheimer’s disease and breast cancer survival. Results DCL consistently outperforms FGS, PC, CPC, and FCI in discovering the parents of the target for the datasets simulated using a simple network. Overall, DCL predicts significantly more datasets correctly (McNemar’s test significance: p<<0. 0001) than any of the other algorithms for these network types. For example, when assessing overall performance (simple and complex network results combined), DCL correctly predicts approximately 1400 more datasets than the top FGS method, 1600 more datasets than the top CPC method, 4500 more datasets than the top PC method, and 5600 more datasets than the top FCI method. Although FGS did correctly predict more datasets than DCL for the complex networks, and DCL correctly predicted only a few more datasets than CPC for these networks, there is no significant difference in performance between these three algorithms for this network type. However, when we use a more continuous measure of accuracy, we find that all the DCL methods are able to better partially predict more direct causes than FGS and CPC for the complex networks. In addition, DCL consistently had faster runtimes than the other algorithms. In the application to the real datasets, DCL identified rs6784615, located on the NISCH gene, and rs10824310, located on the PRKG1 gene, as direct causes of late onset Alzheimer’s disease (LOAD) development. In addition, DCL identified ER category as a direct predictor of breast cancer mortality within 5 years, and HER2 status as a direct predictor of 10-year breast cancer mortality. These predictors have been identified in previous studies to have a direct causal relationship with their respective phenotypes, supporting the predictive power of DCL. When the other algorithms discovered predictors from the real datasets, these predictors were either also found by DCL or could not be supported by previous studies. Conclusion Our results show that DCL outperforms FGS, PC, CPC, and FCI in almost every case, demonstrating its potential to advance causal learning. Furthermore, our DCL algorithm effectively identifies direct causes in the LOAD and Metabric GWAS datasets, which indicates its potential for clinical applications.

Details DOI

AAAI Conference 2014 Conference Paper

ARIA: Asymmetry Resistant Instance Alignment

Sanghoon Lee
Seung-won Hwang

We study the problem of instance alignment between knowledge bases (KBs). Existing approaches, exploiting the “symmetry” of structure and information across KBs, suffer in the presence of asymmetry, which is frequent as KBs are independently built. Specifically, we observe three types of asymmetries (in concepts, in features, and in structures). Our goal is to identify key techniques to reduce accuracy loss caused by each type of asymmetry, then design Asymmetry-Resistant Instance Alignment framework (ARIA). ARIA uses twophased blocking methods considering concept and feature asymmetries, with a novel similarity measure overcoming structure asymmetry. Compared to a state-ofthe-art method, ARIA increased precision by 19% and recall by 2%, and decreased processing time by more than 80% in matching large-scale real-life KBs.

PDF Details

AAAI Conference 2010 Conference Paper

Towards an Intelligent Code Search Engine

Jinhan Kim
Sanghoon Lee
Seung-won Hwang
Sunghun Kim

Software developers increasingly rely on information from the Web, such as documents or code examples on Application Programming Interfaces (APIs), to facilitate their development processes. However, API documents often do not include enough information for developers to fully understand the API usages, while searching for good code examples requires non-trivial effort. To address this problem, we propose a novel code search engine, combining the strength of browsing documents and searching for code examples, by returning documents embedded with high-quality code example summaries mined from the Web. Our evaluation results show that our approach provides code examples with high precision and boosts programmer productivity.

PDF Details