Giljoo Nam — accepted AI-conference papers

2026

DYMO-Hair: Generalizable Volumetric Dynamics Modeling for Robot Hair Manipulation

Chengyang Zhao, Uksang Yoo, Arkadeep Narayan Chaudhury, Giljoo Nam, Jonathan Francis, Jeffrey Ichnowski +1

ICRA 2026poster

Hair care is an essential daily activity, yet it remains inaccessible to individuals with limited mobility and challenging for autonomous robot systems due to the fine-grained physical structure and complex dynamics of hair. In this work, we present DYMO-Hair, a model-based robot hair care system. W…

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

Decoupled Generative Modeling for Human-Object Interaction Synthesis

Hwanhee Jung, Seunggwan Lee, Jeongyoon Yoon, SeungHyeon Kim, Giljoo Nam, Qixing Huang +1

CVPR 2026

Synthesizing realistic human-object interaction (HOI) is essential for 3D computer vision and robotics, underpinning animation and embodied control. Existing approaches often require manually specified intermediate waypoints and place all optimization objectives on a single network, which increases

Cited by 0 Source ↗Scholar ↗

2026

GeoRelight: Learning Joint Geometrical Relighting and Reconstruction with Flexible Multi-Modal Diffusion Transformers

Yuxuan Xue, Ruofan Liang, Egor Zakharov, Timur Bagautdinov, Chen Cao, Giljoo Nam +3

CVPR 2026

Relighting a person from a single photo is an attractive but ill-posed task, as a 2D image ambiguously entangles 3D geometry, intrinsic appearance, and illumination. Current methods either use sequential pipelines that suffer from error accumulation, or they do not explicitly leverage 3D geometry du

Cited by 0 Source ↗Scholar ↗

2026

Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining

Junxuan Li, Rawal Khirodkar, Egor Zakharov, Jihyun Lee, Zhaoen Su, Yuan Dong +34

CVPR 2026

High-quality 3D avatar modeling faces a critical trade-off between fidelity and generalization. On the one hand, multi-view studio data enables high-fidelity modeling of humans with precise control over expressions and poses, but it struggles to generalize to real-world data due to limited scale and

Cited by 0 Source ↗code ↗Scholar ↗

2025

A Real-world Display Inverse Rendering Dataset

Seokjun Choi, Hoon-Gyu Chung, Yujin Jeon, Giljoo Nam, Seung-Hwan Baek

ICCV 2025poster

Inverse rendering aims to reconstruct geometry and reflectance from captured images. Display-camera imaging systems offer unique advantages for this task: each pixel can easily function as a programmable point light source, and the polarized light emitted by LCD displays facilitates diffuse-specular…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars

Byungjun Kim, Shunsuke Saito, Giljoo Nam, Tomas Simon, Jason Saragih, Hanbyul Joo +1

ICCV 2025poster

We present a universal prior model for 3D head avatars with explicit hair compositionality. Existing approaches to build generalizable priors for 3D head avatars often adopt a holistic modeling approach, treating the face and hair as an inseparable entity. This overlooks the inherent compositionalit…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Insightful Instance Features for 3D Instance Segmentation

Wonseok Roh, Hwanhee Jung, Giljoo Nam, Dong In Lee, Hyeongcheol Park, Sang Ho Yoon +2

CVPR 2025poster

Recent 3D Instance Segmentation methods typically encode hundreds of instance-wise candidates with instance-specific information in various ways and refine them into final masks. However, they have yet to fully explore the benefit of these candidates. They overlook the valuable cues encoded in multi…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

LUCAS: Layered Universal Codec Avatars

Di Liu, Teng Deng, Giljoo Nam, Yu Rong, Stanislav Pidhorskyi, Junxuan Li +3

CVPR 2025poster

Photorealistic 3D head avatar reconstruction faces critical challenges in modeling dynamic face-hair interactions and achieving cross-identity generalization, particularly during expressions and head movements. We present LUCAS, a novel Universal Prior Model (UPM) for codec avatar modeling that dise…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Differentiable Display Photometric Stereo

Seokjun Choi, Seungwoo Yoon, Giljoo Nam, Seungyong Lee, Seung-Hwan Baek

CVPR 2024poster

Photometric stereo leverages variations in illumination conditions to reconstruct surface normals. Display photometric stereo which employs a conventional monitor as an illumination source has the potential to overcome limitations often encountered in bulky and difficult-to-use conventional setups.…

Cited by 3 Source ↗PDF ↗Scholar ↗

2024

Doubly Hierarchical Geometric Representations for Strand-based Human Hairstyle Generation

Yunlu Chen, Francisco Vicente Carrasco, Christian Häne, Giljoo Nam, Jean-Charles Bazin, Fernando De la Torre

NeurIPS 2024poster

We introduce a doubly hierarchical generative representation for strand-based 3D hairstyle geometry that progresses from coarse, low-pass filtered guide hair to densely populated hair strands rich in high-frequency details. We employ the Discrete Cosine Transform (DCT) to separate low-frequency stru…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Edge-Aware 3D Instance Segmentation Network with Intelligent Semantic Prior

Wonseok Roh, Hwanhee Jung, Giljoo Nam, Jinseop Yeom, Hyunje Park, Sang Ho Yoon +1

CVPR 2024poster

While recent 3D instance segmentation approaches show promising results based on transformer architectures they often fail to correctly identify instances with similar appearances. They also ambiguously determine edges leading to multiple misclassifications of adjacent edge points. In this work we i…

Cited by 4 Source ↗PDF ↗Scholar ↗

2024

Human Hair Reconstruction with Strand-Aligned 3D Gaussians

Egor Zakharov*, Vanessa Sklyarova, Michael J. Black, Giljoo Nam, Justus Thies, Otmar Hilliges

ECCV 2024poster

"We introduce a new hair modeling method that uses a dual representation of classical hair strands and 3D Gaussians to produce accurate and realistic strand-based reconstructions from multi-view data. In contrast to recent approaches that leverage unstructured Gaussians to model human avatars, our m…

Cited by 9 Source ↗PDF ↗code ↗Scholar ↗

2024

InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion

Jihyun Lee, Shunsuke Saito, Giljoo Nam, Minhyuk Sung, Tae-Kyun Kim

CVPR 2024poster

We present InterHandGen a novel framework that learns the generative prior of two-hand interaction. Sampling from our model yields plausible and diverse two-hand shapes in close interaction with or without an object. Our prior can be incorporated into any optimization or learning methods to reduce a…

Cited by 13 Source ↗PDF ↗Scholar ↗

2024

LRSLAM: Low-rank Representation of Signed Distance Fields in Dense Visual SLAM System

Hongbeen Park, Minjeong Park, Giljoo Nam, Jinkyu Kim*

ECCV 2024poster

"Simultaneous Localization and Mapping (SLAM) has been crucial across various domains, including autonomous driving, mobile robotics, and mixed reality. Dense visual SLAM, leveraging RGB-D camera systems, offers advantages but faces challenges in achieving real-time performance, robustness, and scal…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Relightable Gaussian Codec Avatars

Shunsuke Saito, Gabriel Schwartz, Tomas Simon, Junxuan Li, Giljoo Nam

CVPR 2024poster

The fidelity of relighting is bounded by both geometry and appearance representations. For geometry both mesh and volumetric approaches have difficulty modeling intricate structures like 3D hair geometry. For appearance existing relighting models are limited in fidelity and often too slow to render…

Cited by 94 Source ↗PDF ↗Scholar ↗

2023

NeuWigs: A Neural Dynamic Model for Volumetric Hair Capture and Animation

Ziyan Wang, Giljoo Nam, Tuur Stuyck, Stephen Lombardi, Chen Cao, Jason Saragih +3

CVPR 2023poster

The capture and animation of human hair are two of the major challenges in the creation of realistic avatars for the virtual reality. Both problems are highly challenging, because hair has complex geometry and appearance, as well as exhibits challenging motion. In this paper, we present a two-stage…

Cited by 16 Source ↗PDF ↗Scholar ↗

2022

HVH: Learning a Hybrid Neural Volumetric Representation for Dynamic Hair Performance Capture

Ziyan Wang, Giljoo Nam, Tuur Stuyck, Stephen Lombardi, Michael Zollhöfer, Jessica Hodgins +1

CVPR 2022poster

Capturing and rendering life-like hair is particularly challenging due to its fine geometric structure, complex physical interaction and the non-trivial visual appearance that must be captured. Yet, it is a critical component to create believable avatars. In this paper, we address the aforementioned…

Cited by 20 PDF ↗code ↗Scholar ↗

2022

Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images

Radu Alexandru Rosu, Shunsuke Saito, Ziyan Wang, Chenglei Wu, Sven Behnke, Giljoo Nam

ECCV 2022poster

"We present Neural Strands, a novel learning framework for modeling accurate hair geometry and appearance from multi-view image inputs. The learned hair model can be rendered in real-time from any viewpoint with high-fidelity view-dependent effects. Our model achieves intuitive shape and style contr…

Cited by 44 Source ↗PDF ↗Scholar ↗

2019

Strand-Accurate Multi-View Hair Capture

Giljoo Nam, Chenglei Wu, Min H. Kim, Yaser Sheikh

CVPR 2019oral

Hair is one of the most challenging objects to reconstruct due to its micro-scale structure and a large number of repeated strands with heavy occlusions. In this paper, we present the first method to capture high-fidelity hair geometry with strand-level accuracy. Our method takes three stages to ach…

Cited by 60 PDF ↗Scholar ↗