246 citations · 491 across the 30 of their papers we have counts for
32 papers
High-Fidelity Eye Animatable Neural Radiance Fields for Human Face
Hengfei Wang, Zhongqun Zhang, Yihua Cheng +1
Face rendering using neural radiance fields (NeRF) is a rapidly developing research area in computer vision. While recent methods primarily focus on controlling facial attributes s…
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…
Spectral Graphormer: Spectral Graph-based Transformer for Egocentric Two-Hand Reconstruction using Multi-View Color Images
Tze Ho Elden Tse, Franziska Mueller, Zhengyang Shen +8
We propose a novel transformer-based framework that reconstructs two high fidelity hands from multi-view RGB images. Unlike existing hand pose estimation methods, where one typical…
Investigation of Architectures and Receptive Fields for Appearance-based Gaze Estimation
Yunhan Wang, Xiangwei Shi, Shalini De Mello +2
With the rapid development of deep learning technology in the past decade, appearance-based gaze estimation has attracted great attention from both computer vision and human-comput…
DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation
Runyang Feng, Yixing Gao, Tze Ho Elden Tse +2
Denoising diffusion probabilistic models that were initially proposed for realistic image generation have recently shown success in various perception tasks (e.g., object detection…
Clothes Grasping and Unfolding Based on RGB-D Semantic Segmentation
Xingyu Zhu, Xin Wang, Jonathan Freer +2
Clothes grasping and unfolding is a core step in robotic-assisted dressing. Most existing works leverage depth images of clothes to train a deep learning-based model to recognize s…
HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation
Linfang Zheng, Chen Wang, Yinghan Sun +5
In this paper, we focus on the problem of category-level object pose estimation, which is challenging due to the large intra-category shape variation. 3D graph convolution (3D-GC)…
Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video
Runyang Feng, Yixing Gao, Xueqing Ma +2
Temporal modeling is crucial for multi-frame human pose estimation. Most existing methods directly employ optical flow or deformable convolution to predict full-spectrum motion fie…
Category-Level 6D Object Pose Estimation with Flexible Vector-Based Rotation Representation
Wei Chen, Xi Jia, Zhongqun Zhang +4
In this paper, we propose a novel 3D graph convolution based pipeline for category-level 6D pose and size estimation from monocular RGB-D images. The proposed method leverages an e…
GazeNeRF: 3D-Aware Gaze Redirection with Neural Radiance Fields
Alessandro Ruzzi, Xiangwei Shi, Xi Wang +5
We propose GazeNeRF, a 3D-aware method for the task of gaze redirection. Existing gaze redirection methods operate on 2D images and struggle to generate 3D consistent results. Inst…
SContact: Graph-based Network for 3D Hand-Object Contact Estimation with Semi-Supervised Learning
Tze Ho Elden Tse, Zhongqun Zhang, Kwang In Kim +3
Despite the recent efforts in accurate 3D annotations in hand and object datasets, there still exist gaps in 3D hand and object reconstructions. Existing works leverage contact map…
Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning
Boeun Kim, Hyung Jin Chang, Jungho Kim +1
We propose a new transformer model for the task of unsupervised learning of skeleton motion sequences. The existing transformer model utilized for unsupervised skeleton-based actio…
Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution
Tze Ho Elden Tse, Kwang In Kim, Ales Leonardis +1
Estimating the pose and shape of hands and objects under interaction finds numerous applications including augmented and virtual reality. Existing approaches for hand and object re…
Repurposing Existing Deep Networks for Caption and Aesthetic-Guided Image Cropping
Nora Horanyi, Kedi Xia, Kwang Moo Yi +3
We propose a novel optimization framework that crops a given image based on user description and aesthetics. Unlike existing image cropping methods, where one typically trains a de…
Contrastive Vicinal Space for Unsupervised Domain Adaptation
Jaemin Na, Dongyoon Han, Hyung Jin Chang +1
Recent unsupervised domain adaptation methods have utilized vicinal space between the source and target domains. However, the equilibrium collapse of labels, a problem where the so…
Nesterov Accelerated ADMM for Fast Diffeomorphic Image Registration
Alexander Thorley, Xi Jia, Hyung Jin Chang +8
Deterministic approaches using iterative optimisation have been historically successful in diffeomorphic image registration (DiffIR). Although these approaches are highly accurate,…
Learning a Model-Driven Variational Network for Deformable Image Registration
Xi Jia, Alexander Thorley, Wei Chen +9
Data-driven deep learning approaches to image registration can be less accurate than conventional iterative approaches, especially when training data is limited. To address this wh…
Unsupervised Hyperbolic Representation Learning via Message Passing Auto-Encoders
Jiwoong Park, Junho Cho, Hyung Jin Chang +1
Most of the existing literature regarding hyperbolic embedding concentrate upon supervised learning, whereas the use of unsupervised hyperbolic embedding is less well explored. In…
FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism
Wei Chen, Xi Jia, Hyung Jin Chang +3
In this paper, we focus on category-level 6D pose and size estimation from monocular RGB-D image. Previous methods suffer from inefficient category-level pose feature extraction wh…
Combining Task Predictors via Enhancing Joint Predictability
Kwang In Kim, Christian Richardt, Hyung Jin Chang
Predictor combination aims to improve a (target) predictor of a learning task based on the (reference) predictors of potentially relevant tasks, without having access to the intern…
SeqHAND:RGB-Sequence-Based 3D Hand Pose and Shape Estimation
John Yang, Hyung Jin Chang, Seungeui Lee +1
3D hand pose estimation based on RGB images has been studied for a long time. Most of the studies, however, have performed frame-by-frame estimation based on independent static ima…
Implications of Human Irrationality for Reinforcement Learning
Haiyang Chen, Hyung Jin Chang, Andrew Howes
Recent work in the behavioural sciences has begun to overturn the long-held belief that human decision making is irrational, suboptimal and subject to biases. This turn to the rati…
Class-Attentive Diffusion Network for Semi-Supervised Classification
Jongin Lim, Daeho Um, Hyung Jin Chang +2
Recently, graph neural networks for semi-supervised classification have been widely studied. However, existing methods only use the information of limited neighbors and do not deal…
G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features
Wei Chen, Xi Jia, Hyung Jin Chang +2
In this paper, we propose a novel real-time 6D object pose estimation framework, named G2L-Net. Our network operates on point clouds from RGB-D detection in a divide-and-conquer fa…