activity
20212024
most citedHierarchical Prior Mining for Non-local Multi-View Stereo

2 citations · 4 across the 8 of their papers we have counts for

collaborators

8 papers

cs.CV2024

fCOP: Focal Length Estimation from Category-level Object Priors

Xinyue Zhang, Jiaqi Yang, Xiangting Meng +2

In the realm of computer vision, the perception and reconstruction of the 3D world through vision signals heavily rely on camera intrinsic parameters, which have long been a subjec…

cs.CV2024

3D Single-object Tracking in Point Clouds with High Temporal Variation

Qiao Wu, Kun Sun, Pei An +3

The high temporal variation of the point clouds is the key challenge of 3D single-object tracking (3D SOT). Existing approaches rely on the assumption that the shape variation of t…

cs.CV2024

Instance by Instance: An Iterative Framework for Multi-instance 3D Registration

Xinyue Cao, Xiyu Zhang, Yuxin Cheng +3

Multi-instance registration is a challenging problem in computer vision and robotics, where multiple instances of an object need to be registered in a standard coordinate system. I…

cs.CV20242 cited

Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis

Zhenhui Ye, Tianyun Zhong, Yi Ren +11

One-shot 3D talking portrait generation aims to reconstruct a 3D avatar from an unseen image, and then animate it with a reference video or audio to generate a talking portrait vid…

cs.CV2023

3D Registration with Maximal Cliques

Xiyu Zhang, Jiaqi Yang, Shikun Zhang +1

As a fundamental problem in computer vision, 3D point cloud registration (PCR) aims to seek the optimal pose to align a point cloud pair. In this paper, we present a 3D registratio…

cs.CV20232 cited

Hierarchical Prior Mining for Non-local Multi-View Stereo

Chunlin Ren, Qingshan Xu, Shikun Zhang +1

As a fundamental problem in computer vision, multi-view stereo (MVS) aims at recovering the 3D geometry of a target from a set of 2D images. Recent advances in MVS have shown that…