39 citations · 84 across the 22 of their papers we have counts for
24 papers
2nd Place Solution to the HANDS 2026 Workshop Challenge-Dexterous Grasp Motion Track: Single-Shot Trajectory Warping for Grasp Motion Generation
Muneeb A. Khan, Woojin Kim, Shinwoo Kim +3
This report describes our 2nd place solution to the HANDS 2026 workshop challenge (Dexterous Grasp Motion track) in conjunction with ECCV 2026. In this challenge, we address grasp…
FlexiAvatar: Unified 3D Gaussian Human Avatars Under Arbitrary Body Visibility
Yihalem Yimolal Tiruneh, Muhammad Salman Ali, Uyoung Jeong +5
Reconstructing animatable 3D human avatars from monocular video is a fundamental problem in computer vision with broad applications in AR/VR and digital content creation. Existing…
Multi-THuMBS: Multi-person Tracking of 3D Human Meshes Beyond Video Shots
Jeongwan On, Muhammad Salman Ali, Muneeb A. Khan +6
Tracking multi-person 3D human meshes from in-the-wild videos is a highly challenging problem due to complex interactions, frequent occlusions, and severe truncation inherent in un…
THOM: Generating Physically Plausible Hand-Object Meshes From Text
Uyoung Jeong, Yihalem Yimolal Tiruneh, Hyung Jin Chang +2
Generating photorealistic 3D hand-object interactions (HOIs) from text is important for applications like robotic grasping and AR/VR content creation. In practice, however, achievi…
HandVQA: Diagnosing and Improving Fine-Grained Spatial Reasoning about Hands in Vision-Language Models
MD Khalequzzaman Chowdhury Sayem, Mubarrat Tajoar Chowdhury, Yihalem Yimolal Tiruneh +4
Understanding the fine-grained articulation of human hands is critical in high-stakes settings such as robot-assisted surgery, chip manufacturing, and AR/VR-based human-AI interact…
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation
Uyoung Jeong, Jonathan Freer, Seungryul Baek +2
We study multi-dataset training (MDT) for pose estimation, where skeletal heterogeneity presents a unique challenge that existing methods have yet to address. In traditional domain…
Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects
Zicong Fan, Takehiko Ohkawa, Linlin Yang +21
We interact with the world with our hands and see it through our own (egocentric) perspective. A holistic 3Dunderstanding of such interactions from egocentric views is important fo…
3D Reconstruction of Interacting Multi-Person in Clothing from a Single Image
Junuk Cha, Hansol Lee, Jaewon Kim +3
This paper introduces a novel pipeline to reconstruct the geometry of interacting multi-person in clothing on a globally coherent scene space from a single image. The main challeng…
Dynamic Appearance Modeling of Clothed 3D Human Avatars using a Single Camera
Hansol Lee, Junuk Cha, Yunhoe Ku +2
The appearance of a human in clothing is driven not only by the pose but also by its temporal context, i.e., motion. However, such context has been largely neglected by existing mo…
BoIR: Box-Supervised Instance Representation for Multi-Person Pose Estimation
Uyoung Jeong, Seungryul Baek, Hyung Jin Chang +1
Single-stage multi-person human pose estimation (MPPE) methods have shown great performance improvements, but existing methods fail to disentangle features by individual instances…
IFaceUV: Intuitive Motion Facial Image Generation by Identity Preservation via UV map
Hansol Lee, Yunhoe Ku, Eunseo Kim +1
Reenacting facial images is an important task that can find numerous applications. We proposed IFaceUV, a fully differentiable pipeline that properly combines 2D and 3D information…
HOReeNet: 3D-aware Hand-Object Grasping Reenactment
Changhwa Lee, Junuk Cha, Hansol Lee +3
We present HOReeNet, which tackles the novel task of manipulating images involving hands, objects, and their interactions. Especially, we are interested in transferring objects of…
Image-free Domain Generalization via CLIP for 3D Hand Pose Estimation
Seongyeong Lee, Hansoo Park, Dong Uk Kim +3
RGB-based 3D hand pose estimation has been successful for decades thanks to large-scale databases and deep learning. However, the hand pose estimation network does not operate well…
Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement
Junuk Cha, Muhammad Saqlain, GeonU Kim +2
Estimating 3D poses and shapes in the form of meshes from monocular RGB images is challenging. Obviously, it is more difficult than estimating 3D poses only in the form of skeleton…
Transformer-based Action recognition in hand-object interacting scenarios
Hoseong Cho, Seungryul Baek
This report describes the 2nd place solution to the ECCV 2022 Human Body, Hands, and Activities (HBHA) from Egocentric and Multi-view Cameras Challenge: Action Recognition. This ch…
Transformer-based Global 3D Hand Pose Estimation in Two Hands Manipulating Objects Scenarios
Hoseong Cho, Donguk Kim, Chanwoo Kim +2
This report describes our 1st place solution to ECCV 2022 challenge on Human Body, Hands, and Activities (HBHA) from Egocentric and Multi-view Cameras (hand pose estimation). In th…
Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction
Anil Armagan, Guillermo Garcia-Hernando, Seungryul Baek +32
We study how well different types of approaches generalise in the task of 3D hand pose estimation under single hand scenarios and hand-object interaction. We show that the accuracy…
Sampling Strategies for GAN Synthetic Data
Binod Bhattarai, Seungryul Baek, Rumeysa Bodur +1
Generative Adversarial Networks (GANs) have been used widely to generate large volumes of synthetic data. This data is being utilized for augmenting with real examples in order to…
Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Rendering
Seungryul Baek, Kwang In Kim, Tae-Kyun Kim
Estimating 3D hand meshes from single RGB images is challenging, due to intrinsic 2D-3D mapping ambiguities and limited training data. We adopt a compact parametric 3D hand model t…
Augmented Skeleton Space Transfer for Depth-based Hand Pose Estimation
Seungryul Baek, Kwang In Kim, Tae-Kyun Kim
Crucial to the success of training a depth-based 3D hand pose estimator (HPE) is the availability of comprehensive datasets covering diverse camera perspectives, shapes, and pose v…
Deep Convolutional Decision Jungle for Image Classification
Seungryul Baek, Kwang In Kim, Tae-Kyun Kim
We propose a novel method called deep convolutional decision jungle (CDJ) and its learning algorithm for image classification. The CDJ maintains the structure of standard convoluti…
First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations
Guillermo Garcia-Hernando, Shanxin Yuan, Seungryul Baek +1
In this work we study the use of 3D hand poses to recognize first-person dynamic hand actions interacting with 3D objects. Towards this goal, we collected RGB-D video sequences com…
Real-time Online Action Detection Forests using Spatio-temporal Contexts
Seungryul Baek, Kwang In Kim, Tae-Kyun Kim
Online action detection (OAD) is challenging since 1) robust yet computationally expensive features cannot be straightforwardly used due to the real-time processing requirements an…
Kinematic-Layout-aware Random Forests for Depth-based Action Recognition
Seungryul Baek, Zhiyuan Shi, Masato Kawade +1
In this paper, we tackle the problem of 24 hours-monitoring patient actions in a ward such as "stretching an arm out of the bed", "falling out of the bed", where temporal movements…