Junyong Noh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Junyong Noh has a total of 122 co-authors. Here are the top co-authors by number of shared publications:
- Kwanggyoon Seo
Graduate School of Culture Technology, KAIST
14 shared publications - Seokhyeon Hong
Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea
9 shared publications - Soojin Choi
Visual Media Lab, KAIST
9 shared publications - Chaelin Kim
Visual Media Lab, KAIST
8 shared publications - Amirsaman Ashtari
Graduate School of Culture Technology, Korea Advanced Institute of Science and Technology, 291 Daehak-ro, Daejeon 34141, Republic of Korea
6 shared publications - Sihun Cha
Visual Media Lab, KAIST Republic of Korea
6 shared publications
Latest Publications
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Asiagraphics Workshop on Intelligent Graphics with a Geometric Perspective
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Open AccessAsiagraphics Workshop on Intelligent Graphics with a Geometric Perspective
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-18
ReCHOIR: Contact-guided Human Object Interaction Retargeting to Diverse Characters
We present ReCHOIR, a novel contact-guided motion retargeting method for transferring human object interaction (HOI) motions across diverse humanoid characters. Unlike prior motion retargeting methods that primarily focus on transferring human motion alone, our goal is to preserve not only the semantics of the original body movement but also consistent interaction between the character and the manipulated object, while jointly producing aligned target human and object motions. Given source HOI motion, object geometry, and contact cues extracted from the source interaction, ReCHOIR retargets an HOI sequence to target characters with different skeletal configurations while maintaining both motion semantics and contact-consistent interaction patterns. Our method builds on a Part-Aware Motion Embedding (PAME) autoencoder, which encodes full-body motion into a shared body-part-wise latent space. This representation enables generalization across heterogeneous skeletons while preserving local motion semantics beneficial for part-aware adaptation in HOI retargeting. On top of this representation, we introduce a contact-guided retargeting module and an object motion decoder for HOI retargeting. The contact-guided retargeting module treats the source object interaction as a condition for refining target character motion: object- and contact-related signals are encoded into a body-part-aligned latent representation and injected into decoding through a residual control branch, enabling stronger adaptation in interaction-relevant body regions without discarding the underlying motion prior. In parallel, the object motion decoder predicts a target object motion aligned with the refined target character motion, ensuring that the object trajectory remains consistent with how the interaction is realized by the target character. Experiments and ablation studies across diverse interaction scenarios and target characters demonstrate that ReCHOIR effectively preserves contact timing, contact locations, and overall interaction plausibility.
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-18
Open AccessReCHOIR: Contact-guided Human Object Interaction Retargeting to Diverse Characters
We present ReCHOIR, a novel contact-guided motion retargeting method for transferring human object interaction (HOI) motions across diverse humanoid characters. Unlike prior motion retargeting methods that primarily focus on transferring human motion alone, our goal is to preserve not only the semantics of the original body movement but also consistent interaction between the character and the manipulated object, while jointly producing aligned target human and object motions. Given source HOI motion, object geometry, and contact cues extracted from the source interaction, ReCHOIR retargets an HOI sequence to target characters with different skeletal configurations while maintaining both motion semantics and contact-consistent interaction patterns. Our method builds on a Part-Aware Motion Embedding (PAME) autoencoder, which encodes full-body motion into a shared body-part-wise latent space. This representation enables generalization across heterogeneous skeletons while preserving local motion semantics beneficial for part-aware adaptation in HOI retargeting. On top of this representation, we introduce a contact-guided retargeting module and an object motion decoder for HOI retargeting. The contact-guided retargeting module treats the source object interaction as a condition for refining target character motion: object- and contact-related signals are encoded into a body-part-aligned latent representation and injected into decoding through a residual control branch, enabling stronger adaptation in interaction-relevant body regions without discarding the underlying motion prior. In parallel, the object motion decoder predicts a target object motion aligned with the refined target character motion, ensuring that the object trajectory remains consistent with how the interaction is realized by the target character. Experiments and ablation studies across diverse interaction scenarios and target characters demonstrate that ReCHOIR effectively preserves contact timing, contact locations, and overall interaction plausibility.
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-16
Skinned Motion Retargeting via Artifact-driven Kinematic Prior Refinement
Motion retargeting aims to transfer a source motion to target characters with different skeletal structures, proportions, and body shapes. Although recent neural retargeting methods have improved flexibility across diverse skeletons, target-side geometric artifacts such as self-penetration remain difficult to resolve. Specifically, existing geometry-aware approaches often rely on fixed skeleton templates or implicit geometry-conditioned prediction, requiring a single network to account for target geometry deformation, detect target-side artifacts, and predict the corresponding correction from target geometry alone, which limits their ability to generalize across diverse skeleton structures and body shapes. In this paper, we present a geometry-aware motion retargeting framework that explicitly connects artifacts observed in the posed character geometry to motion refinement while preserving the flexibility of skeleton-agnostic neural retargeting. Our method first learns a motion embedding shared across different skeletons using a transformer-based retargeting autoencoder that transfers motion across arbitrary source-target skeleton pairs. Building on this kinematic motion prior, we introduce an artifact-driven refinement module that observes self-penetration on the posed target mesh and converts it into a corrective cue through a motion-to-vertex Jacobian. We further condition motion decoding on target geometry using skinning weight-based joint-aligned geometry features derived from the rest pose mesh. This design combines explicit target-side artifact reasoning with flexible geometry-aware decoding in a unified framework. Experiments on both fixed and arbitrary skeleton structure settings show that our method improves kinematic retargeting accuracy and reduces geometric artifacts, producing plausible motions across seen and unseen target characters. Code is available at https://seokhyeonhong.github.io/projects/kinematic-refinement/.
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-16
Open AccessSkinned Motion Retargeting via Artifact-driven Kinematic Prior Refinement
Motion retargeting aims to transfer a source motion to target characters with different skeletal structures, proportions, and body shapes. Although recent neural retargeting methods have improved flexibility across diverse skeletons, target-side geometric artifacts such as self-penetration remain difficult to resolve. Specifically, existing geometry-aware approaches often rely on fixed skeleton templates or implicit geometry-conditioned prediction, requiring a single network to account for target geometry deformation, detect target-side artifacts, and predict the corresponding correction from target geometry alone, which limits their ability to generalize across diverse skeleton structures and body shapes. In this paper, we present a geometry-aware motion retargeting framework that explicitly connects artifacts observed in the posed character geometry to motion refinement while preserving the flexibility of skeleton-agnostic neural retargeting. Our method first learns a motion embedding shared across different skeletons using a transformer-based retargeting autoencoder that transfers motion across arbitrary source-target skeleton pairs. Building on this kinematic motion prior, we introduce an artifact-driven refinement module that observes self-penetration on the posed target mesh and converts it into a corrective cue through a motion-to-vertex Jacobian. We further condition motion decoding on target geometry using skinning weight-based joint-aligned geometry features derived from the rest pose mesh. This design combines explicit target-side artifact reasoning with flexible geometry-aware decoding in a unified framework. Experiments on both fixed and arbitrary skeleton structure settings show that our method improves kinematic retargeting accuracy and reduces geometric artifacts, producing plausible motions across seen and unseen target characters. Code is available at https://seokhyeonhong.github.io/projects/kinematic-refinement/.
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-17
Length-varying Neural Motion Stitching via Cluster Transition Graph
Motion stitching aims to create new character animations by seamlessly combining existing motion sequences. Existing approaches often require manual selection of transition range or assume fixed transition length, restricting the types of motions that can be connected. To broaden the diversity of motions that can be synthesized, it is essential to generate transitions of varying lengths, allowing the character sufficient time to adapt its pose when the input motions differ significantly. To this end, we propose a length-varying neural motion stitching method based on a cluster transition graph, which produces naturally connected motion sequences given two distinct input motions. Our framework consists of three stages: motion clustering, cluster pathfinding, and motion generation. First, motion clustering maps input motions to discrete clusters. Next, we identify the corresponding clusters in the cluster transition graph and search for a connecting path. In this graph, nodes represent motion clusters, and directed edges indicate valid transitions between them. The resulting path determines both the transition length and a guide sequence that informs motion generation. Finally, the path and input motions are provided to a Transformer encoder-based motion generator to produce the final transition poses. Experimental results demonstrate that our method adaptively adjusts the motion length and successfully generates plausible transitions between distinct motions, such as crawling, basketball shooting, and slow locomotion. We also show that using a graph structure effectively estimates transition durations and produces high-fidelity results compared to methods that assume a fixed transition length, or directly compute the time. Code is available at Project Page
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-17
Open AccessLength-varying Neural Motion Stitching via Cluster Transition Graph
Motion stitching aims to create new character animations by seamlessly combining existing motion sequences. Existing approaches often require manual selection of transition range or assume fixed transition length, restricting the types of motions that can be connected. To broaden the diversity of motions that can be synthesized, it is essential to generate transitions of varying lengths, allowing the character sufficient time to adapt its pose when the input motions differ significantly. To this end, we propose a length-varying neural motion stitching method based on a cluster transition graph, which produces naturally connected motion sequences given two distinct input motions. Our framework consists of three stages: motion clustering, cluster pathfinding, and motion generation. First, motion clustering maps input motions to discrete clusters. Next, we identify the corresponding clusters in the cluster transition graph and search for a connecting path. In this graph, nodes represent motion clusters, and directed edges indicate valid transitions between them. The resulting path determines both the transition length and a guide sequence that informs motion generation. Finally, the path and input motions are provided to a Transformer encoder-based motion generator to produce the final transition poses. Experimental results demonstrate that our method adaptively adjusts the motion length and successfully generates plausible transitions between distinct motions, such as crawling, basketball shooting, and slow locomotion. We also show that using a graph structure effectively estimates transition durations and produces high-fidelity results compared to methods that assume a fixed transition length, or directly compute the time. Code is available at Project Page
- Open Access
- 1 September 2026
- Published by Korea Computer Graphics Society in Journal of the Korea Computer Graphics Society
- Vol. 32 (4) , 1-12
ChoreoMamba: Long-Sequence Dance Generation with Bidirectional Mamba
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 September 2026
- Published by Korea Computer Graphics Society in Journal of the Korea Computer Graphics Society
- Vol. 32 (4) , 1-12
Open AccessChoreoMamba: Long-Sequence Dance Generation with Bidirectional Mamba
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
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Stylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptation
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessStylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptation
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
PressureBlush: Real-Time Blanching and Hyperemia Shading from Neural Deformation Signals
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessPressureBlush: Real-Time Blanching and Hyperemia Shading from Neural Deformation Signals
- Open Access
- 3 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (4) , 1-17
Skinned Motion Retargeting with Spatially Adaptive Interaction Guidance
Retargeting motion across characters with varying body shapes while preserving interaction semantics, such as self-contact and near-body proximity, remains a challenging problem. While recent geometry-aware approaches address this by maintaining spatial relationships between predefined corresponding regions, their reliance on static correspondences often struggles when the target character exhibits exaggerated body proportions. In this paper, we present a geometry-aware motion retargeting framework that preserves interaction semantics by performing proximity matching over spatially adaptive anchors. Unlike prior methods with static anchor definitions, the proposed method dynamically repositions anchors to reachable regions on the target character. This is achieved via a Transformer-based anchor refinement strategy that predicts anchor displacements and constrains the translated anchors to remain on the target character geometry through differentiable soft projection. By incorporating pose-dependent spatial structures from the source character, the adapted anchors provide structurally coherent guidance for interaction-aware retargeting. Conditioned on these anchors, a graph-based autoencoder predicts target skeletal motion that preserves the spatial configuration of the source. To encourage task-aligned optimization between anchor adaptation and motion retargeting, we adopt an alternating training scheme in which each module is optimized in turn. Through extensive evaluations, we demonstrate that our method outperforms state-of-the-art approaches in preserving interaction fidelity across diverse character geometries. Code is available at Project Page .
- 3 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (4) , 1-17
Open AccessSkinned Motion Retargeting with Spatially Adaptive Interaction Guidance
Retargeting motion across characters with varying body shapes while preserving interaction semantics, such as self-contact and near-body proximity, remains a challenging problem. While recent geometry-aware approaches address this by maintaining spatial relationships between predefined corresponding regions, their reliance on static correspondences often struggles when the target character exhibits exaggerated body proportions. In this paper, we present a geometry-aware motion retargeting framework that preserves interaction semantics by performing proximity matching over spatially adaptive anchors. Unlike prior methods with static anchor definitions, the proposed method dynamically repositions anchors to reachable regions on the target character. This is achieved via a Transformer-based anchor refinement strategy that predicts anchor displacements and constrains the translated anchors to remain on the target character geometry through differentiable soft projection. By incorporating pose-dependent spatial structures from the source character, the adapted anchors provide structurally coherent guidance for interaction-aware retargeting. Conditioned on these anchors, a graph-based autoencoder predicts target skeletal motion that preserves the spatial configuration of the source. To encourage task-aligned optimization between anchor adaptation and motion retargeting, we adopt an alternating training scheme in which each module is optimized in turn. Through extensive evaluations, we demonstrate that our method outperforms state-of-the-art approaches in preserving interaction fidelity across diverse character geometries. Code is available at Project Page .
- Open Access
- 3 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (4) , 1-17
StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition
Creative face stylization aims to render portraits in diverse visual idioms such as cartoons, sketches, and paintings while retaining recognizable identity. However, current identity encoders, which are typically trained and calibrated on natural photographs, exhibit severe brittleness under stylization. They often mistake changes in texture or color palette for identity drift or fail to detect geometric exaggerations. This reveals the lack of a style-agnostic framework to evaluate and supervise identity consistency across varying styles and strengths. To address this gap, we introduce StyleID, a human perception-aware dataset and evaluation framework for facial identity under stylization. StyleID comprises two datasets: (i) StyleBench-H, a benchmark that captures human same-different verification judgments across diffusion- and flow-matching-based stylization at multiple style strengths, and (ii) StyleBench-S, a supervision set derived from psychometric recognition-strength curves obtained through controlled two-alternative forced-choice (2AFC) experiments. Leveraging StyleBench-S, we fine-tune existing semantic encoders to align their similarity orderings with human perception across styles and strengths. Experiments demonstrate that our calibrated models yield significantly higher correlation with human judgments and enhanced robustness for out-of-domain, artist drawn portraits. All of our datasets, code, and pretrained models will be publicly available.
- 3 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (4) , 1-17
Open AccessStyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition
Creative face stylization aims to render portraits in diverse visual idioms such as cartoons, sketches, and paintings while retaining recognizable identity. However, current identity encoders, which are typically trained and calibrated on natural photographs, exhibit severe brittleness under stylization. They often mistake changes in texture or color palette for identity drift or fail to detect geometric exaggerations. This reveals the lack of a style-agnostic framework to evaluate and supervise identity consistency across varying styles and strengths. To address this gap, we introduce StyleID, a human perception-aware dataset and evaluation framework for facial identity under stylization. StyleID comprises two datasets: (i) StyleBench-H, a benchmark that captures human same-different verification judgments across diffusion- and flow-matching-based stylization at multiple style strengths, and (ii) StyleBench-S, a supervision set derived from psychometric recognition-strength curves obtained through controlled two-alternative forced-choice (2AFC) experiments. Leveraging StyleBench-S, we fine-tune existing semantic encoders to align their similarity orderings with human perception across styles and strengths. Experiments demonstrate that our calibrated models yield significantly higher correlation with human judgments and enhanced robustness for out-of-domain, artist drawn portraits. All of our datasets, code, and pretrained models will be publicly available.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-14
ComVi: Context-Aware Optimized Comment Display in Video Playback
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-14
Open AccessComVi: Context-Aware Optimized Comment Display in Video Playback