iFlame: Interleaving Full and Linear Attention for Efficient Mesh Generation

Hanxiao Wang, Biao Zhang📧, Weize Quan, Dong-Ming Yan, Peter Wonka

Project, Code

Geometry Distributions

Biao Zhang, Jing Ren, Peter Wonka

Project, Code

LaGeM: A Large Geometry Model for 3D Representation Learning and Diffusion

Biao Zhang, Peter Wonka

Project, Code, OpenReview

Vivid-ZOO: Multi-View Video Generation with Diffusion Model

Bing Li*, Cheng Zheng*, Wenxuan Zhu*, Jinjie Mai, Biao Zhang, Peter Wonka, Bernard Ghanem

Project, Code

Functional Diffusion

Biao Zhang, Peter Wonka

Project, Code

Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking

Wei Cao*, Chang Luo*, Biao Zhang, Matthias Niessner, Jiapeng Tang

Project, Code

3DShape2VecSet: A 3d shape representation for neural fields and generative diffusion models

Biao Zhang, Peter Wonka

Project, Code (Legacy), Code (Latest), ToG

• The work has been integrated into some large 3D foundation models, such as Tripo, CLAY, and Hunyuan3D.
• I gave a talk about this work in Towards 3D Foundation Models: Progress and Prospects
• Online talk Meshy, GAMES Webinar 1, GAMES Webinar 2

3DILG: Irregular Latent Grids for 3D Generative Modeling

Biao Zhang, Peter Wonka

Project, Code

Training Data Generating Networks: Shape Reconstruction via Bi-level Optimization

Biao Zhang, Peter Wonka

Intuitive and Efficient Roof Modeling for Reconstruction and Synthesis

Jing Ren, Biao Zhang, Bojian Wu, Jianqiang Huang, Lubin Fan, Maks Ovsjanikov, Peter Wonka

Code

Point cloud instance segmentation using probabilistic embeddings

Biao Zhang, Peter Wonka

• Featured in CVPR 2021 ScanNet workshop.