Tengfei WANG

I am currently a researcher at Shanghai AI Lab, working closely with Ziwei Liu . I obtained my PhD degree at the Hong Kong University of Science and Technology (HKUST), advised by Qifeng Chen. I was a research intern at Microsoft Research Asia (MSRA) from 2021 to 2023. I was a research intern at Tencent AI Lab.
I'm interested in AI-based visual content generation, including image, video and 3D assets. I've received HKUST CSE Best PhD Dissertation Award (Honorable Mention) in 2023.

Email  /  Github  /  Google Scholar  /  Linked In

profile photo
News

  • News (Jul 2024): Three papers accepted to ECCV 2024, including one oral paper.
  • News (Apr 2024): One paper accepted to SIGGRAPH 2024.
  • News (Jul 2023): Two papers accepted to ICCV 2023.
  • News (Fed 2023): Two papers accepted to CVPR 2023, including one highlight paper.
  • News (Mar 2022): One paper accepted to CVPR 2022.
  • News (Dec 2021): One paper accepted to AAAI 2022.
  • News (Jul 2021): Two papers accepted to ICCV 2021, including one oral paper.
  • News (Mar 2021): One paper accepted to CVPR 2021.

Open-Source Projects
OpenLRM: Open-Source Large Reconstruction Models
Zexin He^ and Tengfei Wang
code / online demo /

Fast image-to-3D generating in a few seconds.

3DTopia: Large Text-to-3D Generation Model

arxiv / code / online demo / video /

Fast and high-quality text-to-3D generation.

3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion

arxiv / code / project website / online demo / video /

3D DiT with Primirive Representation.

Publications

(*equal contribution, ^intern, †corresponding author)

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE
Yongwei Chen, Yushi Lan, Shangchen Zhou, Tengfei Wang, Xingang Pan
preprint , 2024
arxiv / code / project website /

A 3D auto-regressive model for both 3D generation and understanding.

Material Anything: Generating Materials for Any 3D Object via Diffusion
Xin Huang^, Tengfei Wang , Ziwei Liu, Qing Wang
preprint , 2024
arxiv / code / project website /

A diffusion model generating PBR materials for any 3D mesh.

Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion
Zhenwei Wang*^, Tengfei Wang* , Zexin He^, Gerhard Hancke, Ziwei Liu, Rynson W.H. Lau
preprint , 2024
arxiv / code / project website / video /

A 3D diffusion model with RAG, supporting 3D generation from text, image, and existing 3D models.

Omni6D: Large-Vocabulary 3D Object Dataset for Category-Level 6D Object Pose Estimation
Mengchen Zhang^, Tong Wu, Tai Wang, Tengfei Wang , Ziwei Liu, Dahua Lin
ECCV , 2024
arxiv / code / video / data /

A large and realistic dataset for 6D pose estimation.

LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation
Jiaxiang Tang, Zhaoxi Chen, Xiaokang Chen, Tengfei Wang , Gang Zeng, Ziwei Liu
ECCV , 2024 (Oral Presentation)
arxiv / code / project website / online demo /

Fast and high-resolution 3D generative model with 3D gaussian splattings.

ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance
Yongwei Chen*^, Tengfei Wang* , Tong Wu, Xingang Pan, Kui Jia, Ziwei Liu
ECCV , 2024
arxiv / project website /

Image-to-3D for compositional scenes and objects.

ThemeStation : Generating Theme-Aware 3D Assets from Few Exemplars
Zhenwei Wang^, Tengfei Wang , Gerhard Hancke, Ziwei Liu, Rynson W.H. Lau
ACM SIGGRAPH , 2024
arxiv / code / project website / video /

Create a gallery of 3D assets with a consistent theme via 3D-to-3D generation.

Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior
Junshu Tang, Tengfei Wang , Bo Zhang, Ting Zhang, Ran Yi, Lizhuang Ma, Dong Chen
ICCV , 2023
arxiv / code / project website / video /

Generate 3D objects from a single image by distilling 3D knowledge from 2D diffusion model.

RODIN: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion
Tengfei Wang , Bo Zhang, Ting Zhang, Shuyang Gu, Jianmin Bao, Tadas Baltrusaitis, Jingjing Shen, Dong Chen, Fang Wen, Qifeng Chen, Baining Guo
CVPR, 2023 (Highlight, 2.5% acceptance rate)
arxiv / code / project website / video /

The first 3D diffusion model for generating high-quality 3D digital avatars represented as a neural radiance field.

3D GAN Inversion with Facial Symmetry Prior
Fei Yin, Yong Zhang, Xuan Wang, Tengfei Wang , Xiaoyu Li, Yuan Gong, Yanbo Fan, Xiaodong Cun, Ying Shan, Cengiz Oztireli, Yujiu Yang
CVPR, 2023
arxiv / code / project website /

Pretraining for Image-to-Image Translation
Tengfei Wang , Ting Zhang, Bo Zhang, Hao Ouyang, Dong Chen, Qifeng Chen, Fang Wen
technical report, 2022
arxiv / code / project website / online demo /

A simple and universal framework that brings the power of pretraining to various image-to-image translation tasks.

High-Fidelity GAN Inversion for Image Attribute Editing
Tengfei Wang , Yong Zhang, Yanbo Fan, Jue Wang, Qifeng Chen
CVPR , 2022
arxiv / code / project website / video / colab / online demo /

A novel GAN inversion framework for high-fidelity image and video editng.

Restorable Image Operators with Quasi-Invertible Networks
Hao Ouyang*, Tengfei Wang* , Qifeng Chen
AAAI , 2022
arxiv / code / project website / video /

A general and unified framework for versatile invertible image processing operators.

Dual-Camera Super-Resolution with Aligned Attention Modules
Tengfei Wang *, Jiaxin Xie *, Wenxiu Sun, Qiong Yan, Qifeng Chen
ICCV , 2021 (Oral Presentation, 3.4% acceptance rate)
arxiv / code / project website / dataset / video /

First real-world dual-camera super-resolution approach.
A new high-quality dataset for dual-camera zoom (telephoto and wide-angle).

Internal Video Inpainting by Implicit Long-range Propagation
Hao Ouyang*, Tengfei Wang*, Qifeng Chen
ICCV , 2021
arxiv / code / project website / dataset / video /

A simple yet effective video inpainting method for videos from arbitrary domains.
No training set and pretrained models are needed.

Image Inpainting with External-internal Learning and Monochromic Bottleneck
Tengfei Wang *, Hao Ouyang *, Qifeng Chen
CVPR , 2021
arxiv / code / project website / video /

A novel internal-learning method for guided image colorization

High-Quality Visual Content Creation with Foundation Generative Models
Tengfei Wang
PHD THESIS , 2023
link /

HKUST CSE Best Dissertation Award Honorable Mention

Services
  • Program Committee/Reviewer: CVPR, ICCV, ECCV, SIGGRAPH, SIGGRAPH Asia, NeurIPS, ICLR, ICML, AAAI, 3DV, TOG, TPAMI, IJCV, TVCG, TIP, TMM
  • Assitant Coach of HKUST ACM Team (2019-2023)
Selected Awards
  • CSE Best PhD Dissertation Award Honorable Mention, HKUST
  • Postgraduate Scholarship, HKUST
  • National Scholarship, Education Ministry of China
  • Outstanding Student, Beihang University
  • First-Class Scholarship, Beihang University

Thanks to Jon Barron for sharing the code of his personal webpage.

Hit Counters
HTML Hit Counters