Xin-Yang Zheng

Xin-Yang Zheng

Auto-generated profile, based on publicly available information

Xin-Yang Zheng

Tsinghua University, Beijing, China and VAST, Beijing, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
26 July 2023 in ACM Transactions on Graphics
Verified
Journal Article
Open access
XZXin-Yang Zheng
Xin-Yang Zheng
HPHao Pan
Hao Pan
PWPeng-Shuai Wang
Peng-Shuai Wang
XTXin Tong
Xin Tong
YLYang Liu
Yang Liu
HSHeung-Yeung Shum
Heung-Yeung Shum
Although the recent rapid evolution of 3D generative neural networks greatly improves 3D shape generation, it is still not convenient for ordinary users to create 3D shapes and control the local geometry of generated shapes. To address these challenges, we propose a diffusion-based 3D generation framework --- locally attentional SDF diffusion , to model plausible 3D shapes, via 2D sketch image input. Our method is built on a two-stage diffusion model. The first stage, named occupancy-diffusion , aims to generate a low-resolution occupancy field to approximate the shape shell. The second stage, named SDF-diffusion , synthesizes a high-resolution signed distance field within the occupied voxels determined by the first stage to extract fine geometry. Our model is empowered by a novel view-aware local attention mechanism for image-conditioned shape generation, which takes advantage of 2D image patch features to guide 3D voxel feature learning, greatly improving local controllability and model generalizability. Through extensive experiments in sketch-conditioned and category-conditioned 3D shape generation tasks, we validate and demonstrate the ability of our method to provide plausible and diverse 3D shapes, as well as its superior controllability and generalizability over existing work.

1 August 2022 in Computer Graphics Forum
Verified
Journal Article
Closed access
XZX. Zheng
X. Zheng
YLY. Liu
Y. Liu
PWP. Wang
P. Wang
XTX. Tong
X. Tong

28 August 2025 in Computer Graphics Forum
Verified
Journal Article
Closed access
BXBojun Xiong
Bojun Xiong
SWSi‐Tong Wei
Si‐Tong Wei
XZXin‐Yang Zheng
Xin‐Yang Zheng
YCYan‐Pei Cao
Yan‐Pei Cao
ZLZhouhui Lian
Zhouhui Lian
PWPeng‐Shuai Wang
Peng‐Shuai Wang

13 July 2024
Verified
Conference Paper
Open access
XZXin-Yang Zheng
Xin-Yang Zheng
HPHao Pan
Hao Pan
YGYu-Xiao Guo
Yu-Xiao Guo
XTXin Tong
Xin Tong
YLYang Liu
Yang Liu
Multiview diffusion (MVD) has emerged as a prominent 3D generation technique, acclaimed for its generalizability, quality, and efficiency. MVD models finetune image diffusion models with 3D data to generate multiple views of a 3D object from an image or text prompt, followed by a multiview 3D reconstruction process. However, the sparsity of views and inconsistent details in the generated multiview images pose challenges for 3D reconstruction. We present MVD2, an efficient 3D reconstruction method tailored for MVD images. MVD2 integrates multiview image features into a 3D feature volume, then transforms this volume into a textureless 3D mesh, onto which the MVD images are mapped as textures. It employs a simple-yet-efficient view-dependent training scheme to mitigate discrepancies between MVD images and ground-truth views of 3D shapes, effectively improving 3D generation quality and robustness. MVD2 is trained with 3D collections and MVD images, and the trained MVD2 efficiently reconstructs 3D meshes from multiview images within one second and exhibits great model generalizability in dealing with images generated by various MVD methods. Our code and the pretrained model are available at: https://zhengxinyang.github.io/projects/MVD_square.html.

14 December 2025
Verified
Conference Paper
Open access
HXHao Xu
Hao Xu
YZYuqing Zhang
Yuqing Zhang
YWYiqian Wu
Yiqian Wu
XZXinyang Zheng
Xinyang Zheng
YLYutao Liu
Yutao Liu
XJXiaogang Jin
Xiaogang Jin