40 citations · 153 across the 38 of their papers we have counts for
20 papers · 1 filter
Stereo-Inertial Poser: Towards Metric-Accurate Shape-Aware Motion Capture Using Sparse IMUs and a Single Stereo Camera
Tutian Tang, Xingyu Ji, Yutong Li +3
Recent advancements in visual-inertial motion capture systems have demonstrated the potential of combining monocular cameras with sparse inertial measurement units (IMUs) as cost-e…
Dynamic Reconstruction of Hand-Object Interaction with Distributed Force-aware Contact Representation
Zhenjun Yu, Wenqiang Xu, Pengfei Xie +4
We present ViTaM-D, a novel visual-tactile framework for reconstructing dynamic hand-object interaction with distributed tactile sensing to enhance contact modeling. Existing metho…
MS-MANO: Enabling Hand Pose Tracking with Biomechanical Constraints
Pengfei Xie, Wenqiang Xu, Tutian Tang +2
This work proposes a novel learning framework for visual hand dynamics analysis that takes into account the physiological aspects of hand motion. The existing models, which are sim…
RFTrans: Leveraging Refractive Flow of Transparent Objects for Surface Normal Estimation and Manipulation
Tutian Tang, Jiyu Liu, Jieyi Zhang +3
Transparent objects are widely used in our daily lives, making it important to teach robots to interact with them. However, it's not easy because the reflective and refractive effe…
Visual-Tactile Sensing for In-Hand Object Reconstruction
Wenqiang Xu, Zhenjun Yu, Han Xue +3
Tactile sensing is one of the modalities humans rely on heavily to perceive the world. Working with vision, this modality refines local geometry structure, measures deformation at…
GarmentTracking: Category-Level Garment Pose Tracking
Han Xue, Wenqiang Xu, Jieyi Zhang +5
Garments are important to humans. A visual system that can estimate and track the complete garment pose can be useful for many downstream tasks and real-world applications. In this…
AKB-48: A Real-World Articulated Object Knowledge Base
Liu Liu, Wenqiang Xu, Haoyuan Fu +3
Human life is populated with articulated objects. A comprehensive understanding of articulated objects, namely appearance, structure, physics property, and semantics, will benefit…
iSeg3D: An Interactive 3D Shape Segmentation Tool
Sucheng Qian, Liu Liu, Wenqiang Xu +1
A large-scale dataset is essential for learning good features in 3D shape understanding, but there are only a few datasets that can satisfy deep learning training. One of the major…
OMAD: Object Model with Articulated Deformations for Pose Estimation and Retrieval
Han Xue, Liu Liu, Wenqiang Xu +2
Articulated objects are pervasive in daily life. However, due to the intrinsic high-DoF structure, the joint states of the articulated objects are hard to be estimated. To model ar…
ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis
Kailin Li, Lixin Yang, Xinyu Zhan +4
Estimating the articulated 3D hand-object pose from a single RGB image is a highly ambiguous and challenging problem, requiring large-scale datasets that contain diverse hand poses…
ContourRender: Detecting Arbitrary Contour Shape For Instance Segmentation In One Pass
Tutian Tang, Wenqiang Xu, Ruolin Ye +2
Direct contour regression for instance segmentation is a challenging task. Previous works usually achieve it by learning to progressively refine the contour prediction or adopting…
Towards Real-World Category-level Articulation Pose Estimation
Liu Liu, Han Xue, Wenqiang Xu +2
Human life is populated with articulated objects. Current Category-level Articulation Pose Estimation (CAPE) methods are studied under the single-instance setting with a fixed kine…
H2O: A Benchmark for Visual Human-human Object Handover Analysis
Ruolin Ye, Wenqiang Xu, Zhendong Xue +3
Object handover is a common human collaboration behavior that attracts attention from researchers in Robotics and Cognitive Science. Though visual perception plays an important rol…
HandTailor: Towards High-Precision Monocular 3D Hand Recovery
Jun Lv, Wenqiang Xu, Lixin Yang +3
3D hand pose estimation and shape recovery are challenging tasks in computer vision. We introduce a novel framework HandTailor, which combines a learning-based hand module and an o…
Learning Universal Shape Dictionary for Realtime Instance Segmentation
Tutian Tang, Wenqiang Xu, Ruolin Ye +2
We present a novel explicit shape representation for instance segmentation. Based on how to model the object shape, current instance segmentation systems can be divided into two ca…
CPF: Learning a Contact Potential Field to Model the Hand-Object Interaction
Lixin Yang, Xinyu Zhan, Kailin Li +3
Modeling the hand-object (HO) interaction not only requires estimation of the HO pose, but also pays attention to the contact due to their interaction. Significant progress has bee…
BiHand: Recovering Hand Mesh with Multi-stage Bisected Hourglass Networks
Lixin Yang, Jiasen Li, Wenqiang Xu +2
3D hand estimation has been a long-standing research topic in computer vision. A recent trend aims not only to estimate the 3D hand joint locations but also to recover the mesh mod…
RGB-D Individual Segmentation
Wenqiang Xu, Yanjun Fu, Yuchen Luo +2
Fine-grained recognition task deals with sub-category classification problem, which is important for real-world applications. In this work, we are particularly interested in the se…
Explicit Shape Encoding for Real-Time Instance Segmentation
Wenqiang Xu, Haiyang Wang, Fubo Qi +1
In this paper, we propose a novel top-down instance segmentation framework based on explicit shape encoding, named \textbf{ESE-Seg}. It largely reduces the computational consumptio…
SRDA: Generating Instance Segmentation Annotation Via Scanning, Reasoning And Domain Adaptation
Wenqiang Xu, Yonglu Li, Cewu Lu
Instance segmentation is a problem of significance in computer vision. However, preparing annotated data for this task is extremely time-consuming and costly. By combining the adva…