53 citations · 121 across the 14 of their papers we have counts for
14 papers
EgoLocate: Real-time Motion Capture, Localization, and Mapping with Sparse Body-mounted Sensors
Xinyu Yi, Yuxiao Zhou, Marc Habermann +4
Human and environment sensing are two important topics in Computer Vision and Graphics. Human motion is often captured by inertial sensors, while the environment is mostly reconstr…
EditableNeRF: Editing Topologically Varying Neural Radiance Fields by Key Points
Chengwei Zheng, Wenbin Lin, Feng Xu
Neural radiance fields (NeRF) achieve highly photo-realistic novel-view synthesis, but it's a challenging problem to edit the scenes modeled by NeRF-based methods, especially for d…
ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision
Jingwang Ling, Zhibo Wang, Feng Xu
By supervising camera rays between a scene and multi-view image planes, NeRF reconstructs a neural scene representation for the task of novel view synthesis. On the other hand, sha…
Physical Interaction: Reconstructing Hand-object Interactions with Physics
Haoyu Hu, Xinyu Yi, Hao Zhang +2
Single view-based reconstruction of hand-object interaction is challenging due to the severe observation missing caused by occlusions. This paper proposes a physics-based method to…
Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Data
Junfeng Lyu, Zhibo Wang, Feng Xu
In portraits, eyeglasses may occlude facial regions and generate cast shadows on faces, which degrades the performance of many techniques like face verification and expression reco…
Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensors
Xinyu Yi, Yuxiao Zhou, Marc Habermann +4
Motion capture from sparse inertial sensors has shown great potential compared to image-based approaches since occlusions do not lead to a reduced tracking quality and the recordin…
OcclusionFusion: Occlusion-aware Motion Estimation for Real-time Dynamic 3D Reconstruction
Wenbin Lin, Chengwei Zheng, Jun-Hai Yong +1
RGBD-based real-time dynamic 3D reconstruction suffers from inaccurate inter-frame motion estimation as errors may accumulate with online tracking. This problem is even more severe…
TransPose: Real-time 3D Human Translation and Pose Estimation with Six Inertial Sensors
Xinyu Yi, Yuxiao Zhou, Feng Xu
Motion capture is facing some new possibilities brought by the inertial sensing technologies which do not suffer from occlusion or wide-range recordings as vision-based solutions d…
Monocular Real-time Full Body Capture with Inter-part Correlations
Yuxiao Zhou, Marc Habermann, Ikhsanul Habibie +3
We present the first method for real-time full body capture that estimates shape and motion of body and hands together with a dynamic 3D face model from a single color image. Our a…
Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data
Yuxiao Zhou, Marc Habermann, Weipeng Xu +3
We present a novel method for monocular hand shape and pose estimation at unprecedented runtime performance of 100fps and at state-of-the-art accuracy. This is enabled by a new lea…
A Closed-form Solution to Universal Style Transfer
Ming Lu, Hao Zhao, Anbang Yao +3
Universal style transfer tries to explicitly minimize the losses in feature space, thus it does not require training on any pre-defined styles. It usually uses different layers of…
DenseAttentionSeg: Segment Hands from Interacted Objects Using Depth Input
Zihao Bo, Hao Zhang, Junhai Yong +1
We propose a real-time DNN-based technique to segment hand and object of interacting motions from depth inputs. Our model is called DenseAttentionSeg, which contains a dense attent…
Real-time Indoor Scene Reconstruction with RGBD and Inertia Input
Zunjie Zhu, Feng Xu
Camera motion estimation is a key technique for 3D scene reconstruction and Simultaneous localization and mapping (SLAM). To make it be feasibly achieved, previous works usually as…
Depth Assisted Full Resolution Network for Single Image-based View Synthesis
Xiaodong Cun, Feng Xu, Chi-Man Pun +1
Researches in novel viewpoint synthesis majorly focus on interpolation from multi-view input images. In this paper, we focus on a more challenging and ill-posed problem that is to…