Junzhe Zhang

Junzhe Zhang

Auto-generated profile, based on publicly available information

Junzhe Zhang

Nanyang Technological University

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 April 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
LPLiang Pan
Liang Pan
XCXinyi Chen
Xinyi Chen
ZCZhongang Cai
Zhongang Cai
JZJunzhe Zhang
Junzhe Zhang
HZHaiyu Zhao
Haiyu Zhao
ZLZiwei Liu
Ziwei Liu
Real-scanned point clouds are often incomplete due to viewpoint, occlusion, and noise, which hampers 3D geometric modeling and perception. Existing point cloud completion methods tend to generate global shape skeletons and hence lack fine local details. Furthermore, they mostly learn a deterministic partial-to-complete mapping, but overlook structural relations in man-made objects. To tackle these challenges, this paper proposes a variational framework, V ariational R elational point C ompletion network (VRCNet) with two appealing properties: 1) Probabilistic Modeling. In particular, we propose a dual-path architecture to enable principled probabilistic modeling across partial and complete clouds. One path consumes complete point clouds for reconstruction by learning a point VAE. The other path generates complete shapes for partial point clouds, whose embedded distribution is guided by distribution obtained from the reconstruction path during training. 2) Relational Enhancement. Specifically, we carefully design point self-attention kernel and point selective kernel module to exploit relational point features, which refines local shape details conditioned on the coarse completion. In addition, we contribute multi-view partial point cloud datasets (MVP and MVP-40 dataset) containing over 200,000 high-quality scans, which render partial 3D shapes from 26 uniformly distributed camera poses for each 3D CAD model. Extensive experiments demonstrate that VRCNet outperforms state-of-the-art methods on all standard point cloud completion benchmarks. Notably, VRCNet shows great generalizability and robustness on real-world point cloud scans. Moreover, we can achieve robust 3D classification for partial point clouds with the help of VRCNet, which can highly increase classification accuracy.


23 October 2022
Verified
Book Chapter
Closed access
PDF file
JZJunzhe Zhang
Junzhe Zhang
DRDaxuan Ren
Daxuan Ren
ZCZhongang Cai
Zhongang Cai
CYChai Kiat Yeo
Chai Kiat Yeo
BDBo Dai
Bo Dai
CLChen Change Loy
Chen Change Loy

2 August 2023 in Results in Engineering
Verified
Journal Article
Open access
ZJZhang Junzhe
Zhang Junzhe
JFJiang Fuqiang
Jiang Fuqiang
CYChen Yupeng
Chen Yupeng
WWWu Weiyi
Wu Weiyi
WQWu Qing
Wu Qing

20 July 2022 in arXiv
Verified
Preprint
Open access
PDF file
JZJunzhe Zhang
Junzhe Zhang
DRDaxuan Ren
Daxuan Ren
ZCZhongang Cai
Zhongang Cai
CYChai Kiat Yeo
Chai Kiat Yeo
BDBo Dai
Bo Dai
CLChen Change Loy
Chen Change Loy
Recovering a textured 3D mesh from a monocular image is highly challenging, particularly for in-the-wild objects that lack 3D ground truths. In this work, we present MeshInversion, a novel framework to improve the reconstruction by exploiting the generative prior of a 3D GAN pre-trained for 3D textured mesh synthesis. Reconstruction is achieved by searching for a latent space in the 3D GAN that best resembles the target mesh in accordance with the single view observation. Since the pre-trained GAN encapsulates rich 3D semantics in terms of mesh geometry and texture, searching within the GAN manifold thus naturally regularizes the realness and fidelity of the reconstruction. Importantly, such regularization is directly applied in the 3D space, providing crucial guidance of mesh parts that are unobserved in the 2D space. Experiments on standard benchmarks show that our framework obtains faithful 3D reconstructions with consistent geometry and texture across both observed and unobserved parts. Moreover, it generalizes well to meshes that are less commonly seen, such as the extended articulation of deformable objects. Code is released at https://github.com/junzhezhang/mesh-inversion