Publications (9)
ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction
Zhengdi Yu, Shaoli Huang, Chen Fang +2
Reconstructing two hands from monocular RGB images is challenging due to frequent occlusion and mutual confusion. Existing methods mainly learn an entangled representation to encod…
P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching
Bing Wang, Changhao Chen, Zhaopeng Cui +8
Accurately describing and detecting 2D and 3D keypoints is crucial to establishing correspondences across images and point clouds. Despite a plethora of learning-based 2D or 3D loc…
Towards Dynamic 3D Reconstruction of Hand-Instrument Interaction in Ophthalmic Surgery
Ming Hu, Zhengdi Yu, Feilong Tang +7
Accurate 3D reconstruction of hands and instruments is critical for vision-based analysis of ophthalmic microsurgery, yet progress has been hampered by the lack of realistic, large…
Geometric Neural Distance Fields for Learning Human Motion Priors
Zhengdi Yu, Simone Foti, Linguang Zhang +4
We introduce Neural Riemannian Motion Fields (NRMF), a novel 3D generative human motion prior that enables robust, temporally consistent, and physically plausible 3D motion recover…
Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera
Zhengdi Yu, Stefanos Zafeiriou, Tolga Birdal
We propose Dyn-HaMR, to the best of our knowledge, the first approach to reconstruct 4D global hand motion from monocular videos recorded by dynamic cameras in the wild. Reconstruc…
SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark
Zhengdi Yu, Shaoli Huang, Yongkang Cheng +1
We present SignAvatars, the first large-scale, multi-prompt 3D sign language (SL) motion dataset designed to bridge the communication gap for Deaf and hard-of-hearing individuals.…
U3DS: Unsupervised 3D Semantic Scene Segmentation
Jiaxu Liu, Zhengdi Yu, Toby P. Breckon +1
Contemporary point cloud segmentation approaches largely rely on richly annotated 3D training data. However, it is both time-consuming and challenging to obtain consistently accura…
Decomposed Human Motion Prior for Video Pose Estimation via Adversarial Training
Wenshuo Chen, Xiang Zhou, Zhengdi Yu +2
Estimating human pose from video is a task that receives considerable attention due to its applicability in numerous 3D fields. The complexity of prior knowledge of human body move…
RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds
Bing Wang, Zhengdi Yu, Bo Yang +5
We present RangeUDF, a new implicit representation based framework to recover the geometry and semantics of continuous 3D scene surfaces from point clouds. Unlike occupancy fields…