Zhengdi Yu
YOU?
Author Swipe
View article: Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera
Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera Open
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. Reconstructing accurate 3D hand meshes from monocular videos is a cru…
View article: U3DS<sup>3</sup>: Unsupervised 3D Semantic Scene Segmentation
U3DS<sup>3</sup>: Unsupervised 3D Semantic Scene Segmentation Open
Contemporary point cloud segmentation approaches largely rely on richly annotated 3D training data. However , it is both time-consuming and challenging to obtain consistently accurate annotations for such 3D scene data. Moreover, there is …
View article: U3DS$^3$: Unsupervised 3D Semantic Scene Segmentation
U3DS$^3$: Unsupervised 3D Semantic Scene Segmentation Open
Contemporary point cloud segmentation approaches largely rely on richly annotated 3D training data. However, it is both time-consuming and challenging to obtain consistently accurate annotations for such 3D scene data. Moreover, there is s…
View article: SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark
SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark Open
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. While there has been an exponentially growing number of res…
View article: ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction
ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction Open
Reconstructing two hands from monocular RGB images is challenging due to frequent occlusion and mutual confusion. Existing methods mainly learn an entangled representation to encode two interacting hands, which are incredibly fragile to im…
View article: Decomposed Human Motion Prior for Video Pose Estimation via Adversarial Training
Decomposed Human Motion Prior for Video Pose Estimation via Adversarial Training Open
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 movements poses a challenge to neural network models in the tas…
View article: ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction
ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction Open
Reconstructing two hands from monocular RGB images is challenging due to frequent occlusion and mutual confusion. Existing methods mainly learn an entangled representation to encode two interacting hands, which are incredibly fragile to im…
View article: RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds
RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds Open
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 or signed distance fields which can only model closed 3D su…
View article: P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching
P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching Open
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 local feature descriptors and detectors having been proposed, …