Taehyun Rhee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Taehyun Rhee has a total of 56 co-authors. Here are the top co-authors by number of shared publications:
- Andrew Chalmers
Victoria University of Wellington
11 shared publications - Junhong Zhao
Centre for Data Science and Artificial Intelligence & School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand
5 shared publications - Faisal Zaman
School of Design Innovation, Victoria University of Wellington, Wellington, New Zealand
4 shared publications - Simon Finnie
Computational Media Innovation Centre, Victoria University of Wellington, Wellington, New Zealand
4 shared publications - John Peter Lewis
Victoria University of Wellington
3 shared publications - Kwanguk Kim
Department of Computer Science, Hanyang University, Seoul, Republic of Korea
3 shared publications
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Flashover: Spatial Storytelling of Wildfire from Memory to Spatial Experience
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessFlashover: Spatial Storytelling of Wildfire from Memory to Spatial Experience
- Open Access
- 1 July 2026
- Published by Korea Computer Graphics Society in Journal of the Korea Computer Graphics Society
- Vol. 32 (3) , 23-33
Exploring the Potential of Electrical Muscle Stimulation-based Guidance in Remote Physical Activity Education
사단법인 한국컴퓨터그래픽스학회의 논문지로서 그래픽스 분야와 그에 연관된 연구영역의 새로운 발견과 최첨단 연구결과를 발표하는 토론의 장입니다. 학회를 대표하는 학술지인 논문지는 1995년에 논문지 발간을 시작으로 2000년부터 3월, 6월, 9월, 12월 총 4회 발간되었고, 2015년부터는 KCGS 학술대회 특별호를 7월에 발간하면서 총 5회 발간되고 있습니다.
- 1 July 2026
- Published by Korea Computer Graphics Society in Journal of the Korea Computer Graphics Society
- Vol. 32 (3) , 23-33
Open AccessExploring the Potential of Electrical Muscle Stimulation-based Guidance in Remote Physical Activity Education
사단법인 한국컴퓨터그래픽스학회의 논문지로서 그래픽스 분야와 그에 연관된 연구영역의 새로운 발견과 최첨단 연구결과를 발표하는 토론의 장입니다. 학회를 대표하는 학술지인 논문지는 1995년에 논문지 발간을 시작으로 2000년부터 3월, 6월, 9월, 12월 총 4회 발간되었고, 2015년부터는 KCGS 학술대회 특별호를 7월에 발간하면서 총 5회 발간되고 있습니다.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-16
Affective and Cognitive Feedback from a Robot for Human-attributed Failure Handling
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-16
Open AccessAffective and Cognitive Feedback from a Robot for Human-attributed Failure Handling
- Open Access
SE360: Semantic Edit in 360$^\circ$ Panoramas via Hierarchical Data Construction
While instruction-based image editing is emerging, extending it to 360$^\circ$ panoramas introduces additional challenges. Existing methods often produce implausible results in both equirectangular projections (ERP) and perspective views. To address these limitations, we propose SE360, a novel framework for multi-condition guided object editing in 360$^\circ$ panoramas. At its core is a novel coarse-to-fine autonomous data generation pipeline without manual intervention. This pipeline leverages a Vision-Language Model (VLM) and adaptive projection adjustment for hierarchical analysis, ensuring the holistic segmentation of objects and their physical context. The resulting data pairs are both semantically meaningful and geometrically consistent, even when sourced from unlabeled panoramas. Furthermore, we introduce a cost-effective, two-stage data refinement strategy to improve data realism and mitigate model overfitting to erase artifacts. Based on the constructed dataset, we train a Transformer-based diffusion model to allow flexible object editing guided by text, mask, or reference image in 360$^\circ$ panoramas. Our experiments demonstrate that our method outperforms existing methods in both visual quality and semantic accuracy.
Open AccessSE360: Semantic Edit in 360$^\circ$ Panoramas via Hierarchical Data Construction
While instruction-based image editing is emerging, extending it to 360$^\circ$ panoramas introduces additional challenges. Existing methods often produce implausible results in both equirectangular projections (ERP) and perspective views. To address these limitations, we propose SE360, a novel framework for multi-condition guided object editing in 360$^\circ$ panoramas. At its core is a novel coarse-to-fine autonomous data generation pipeline without manual intervention. This pipeline leverages a Vision-Language Model (VLM) and adaptive projection adjustment for hierarchical analysis, ensuring the holistic segmentation of objects and their physical context. The resulting data pairs are both semantically meaningful and geometrically consistent, even when sourced from unlabeled panoramas. Furthermore, we introduce a cost-effective, two-stage data refinement strategy to improve data realism and mitigate model overfitting to erase artifacts. Based on the constructed dataset, we train a Transformer-based diffusion model to allow flexible object editing guided by text, mask, or reference image in 360$^\circ$ panoramas. Our experiments demonstrate that our method outperforms existing methods in both visual quality and semantic accuracy.
- Open Access
Parameter-Free Neural Lens Blur Rendering for High-Fidelity Composites
Consistent and natural camera lens blur is important for seamlessly blending 3D virtual objects into photographed real-scenes. Since lens blur typically varies with scene depth, the placement of virtual objects and their corresponding blur levels significantly affect the visual fidelity of mixed reality compositions. Existing pipelines often rely on camera parameters (e.g., focal length, focus distance, aperture size) and scene depth to compute the circle of confusion (CoC) for realistic lens blur rendering. However, such information is often unavailable to ordinary users, limiting the accessibility and generalizability of these methods. In this work, we propose a novel compositing approach that directly estimates the CoC map from RGB images, bypassing the need for scene depth or camera metadata. The CoC values for virtual objects are inferred through a linear relationship between its signed CoC map and depth, and realistic lens blur is rendered using a neural reblurring network. Our method provides flexible and practical solution for real-world applications. Experimental results demonstrate that our method achieves high-fidelity compositing with realistic defocus effects, outperforming state-of-the-art techniques in both qualitative and quantitative evaluations.
Open AccessParameter-Free Neural Lens Blur Rendering for High-Fidelity Composites
Consistent and natural camera lens blur is important for seamlessly blending 3D virtual objects into photographed real-scenes. Since lens blur typically varies with scene depth, the placement of virtual objects and their corresponding blur levels significantly affect the visual fidelity of mixed reality compositions. Existing pipelines often rely on camera parameters (e.g., focal length, focus distance, aperture size) and scene depth to compute the circle of confusion (CoC) for realistic lens blur rendering. However, such information is often unavailable to ordinary users, limiting the accessibility and generalizability of these methods. In this work, we propose a novel compositing approach that directly estimates the CoC map from RGB images, bypassing the need for scene depth or camera metadata. The CoC values for virtual objects are inferred through a linear relationship between its signed CoC map and depth, and realistic lens blur is rendered using a neural reblurring network. Our method provides flexible and practical solution for real-world applications. Experimental results demonstrate that our method achieves high-fidelity compositing with realistic defocus effects, outperforming state-of-the-art techniques in both qualitative and quantitative evaluations.
- Open Access
TouchWalker: Real-Time Avatar Locomotion from Touchscreen Finger Walking
We present TouchWalker, a real-time system for controlling full-body avatar locomotion using finger-walking gestures on a touchscreen. The system comprises two main components: TouchWalker-MotionNet, a neural motion generator that synthesizes full-body avatar motion on a per-frame basis from temporally sparse two-finger input, and TouchWalker-UI, a compact touch interface that interprets user touch input to avatar-relative foot positions. Unlike prior systems that rely on symbolic gesture triggers or predefined motion sequences, TouchWalker uses its neural component to generate continuous, context-aware full-body motion on a per-frame basis-including airborne phases such as running, even without input during mid-air steps-enabling more expressive and immediate interaction. To ensure accurate alignment between finger contacts and avatar motion, it employs a MoE-GRU architecture with a dedicated foot-alignment loss. We evaluate TouchWalker in a user study comparing it to a virtual joystick baseline with predefined motion across diverse locomotion tasks. Results show that TouchWalker improves users' sense of embodiment, enjoyment, and immersion.
Open AccessTouchWalker: Real-Time Avatar Locomotion from Touchscreen Finger Walking
We present TouchWalker, a real-time system for controlling full-body avatar locomotion using finger-walking gestures on a touchscreen. The system comprises two main components: TouchWalker-MotionNet, a neural motion generator that synthesizes full-body avatar motion on a per-frame basis from temporally sparse two-finger input, and TouchWalker-UI, a compact touch interface that interprets user touch input to avatar-relative foot positions. Unlike prior systems that rely on symbolic gesture triggers or predefined motion sequences, TouchWalker uses its neural component to generate continuous, context-aware full-body motion on a per-frame basis-including airborne phases such as running, even without input during mid-air steps-enabling more expressive and immediate interaction. To ensure accurate alignment between finger contacts and avatar motion, it employs a MoE-GRU architecture with a dedicated foot-alignment loss. We evaluate TouchWalker in a user study comparing it to a virtual joystick baseline with predefined motion across diverse locomotion tasks. Results show that TouchWalker improves users' sense of embodiment, enjoyment, and immersion.
- 7 December 2024
- Published by Springer Nature
- p. 165-181
Full-Body Human De-lighting with Semi-supervised Learning
- 7 December 2024
- Published by Springer Nature
- p. 165-181
Full-Body Human De-lighting with Semi-supervised Learning
- 30 March 2024
- Published by Springer Nature
- p. 74-90
Neural Radiance Fields for Dynamic View Synthesis Using Local Temporal Priors
- 30 March 2024
- Published by Springer Nature
- p. 74-90
Neural Radiance Fields for Dynamic View Synthesis Using Local Temporal Priors
- Open Access
- 12 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1
Real-time Auditorium Modeling and Visual Effects for Live Performances
- 12 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1
Open AccessReal-time Auditorium Modeling and Visual Effects for Live Performances
- Open Access
- 28 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-4
A Motion-Simulation Platform to Generate Synthetic Motion Data for Computer Vision Tasks
We developed the Motion-Simulation Platform, a platform running within a game engine that is able to extract both RGB imagery and the corresponding intrinsic motion data (i.e., motion field). This is useful for motion-related computer vision tasks where large amounts of intrinsic motion data are required to train a model. We describe the implementation and design details of the Motion-Simulation Platform. The platform is extendable, such that any scene developed within the game engine is able to take advantage of the motion data extraction tools. We also provide both user and AI-bot controlled navigation, enabling user-driven input and mass automation of motion data collection.
- 28 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessA Motion-Simulation Platform to Generate Synthetic Motion Data for Computer Vision Tasks
We developed the Motion-Simulation Platform, a platform running within a game engine that is able to extract both RGB imagery and the corresponding intrinsic motion data (i.e., motion field). This is useful for motion-related computer vision tasks where large amounts of intrinsic motion data are required to train a model. We describe the implementation and design details of the Motion-Simulation Platform. The platform is extendable, such that any scene developed within the game engine is able to take advantage of the motion data extraction tools. We also provide both user and AI-bot controlled navigation, enabling user-driven input and mass automation of motion data collection.