Ziqi Huang

Ziqi Huang is a Ph.D. student at MMLab@NTU, Nanyang Technological University, supervised by Prof. Ziwei Liu. She is broadly interested in computer vision and deep learning. She currently works on generative models, visual generation and manipulation.

Ziqi obtained her Bachelor’s degree (2022) from NTU, School of Electrical and Electronic Engineering. She is awarded the Google PhD Fellowship 2023.

Google Scholar / GitHub / Twitter / Email

News

∙ [2024-02] Two papers accepted to CVPR 2024
∙ [2023-12] We are organizing Women in Computer Vision (WiCV) Workshop at CVPR 2024
∙ [2023-11] We released VBench, a comprehensive benchmark for evaluating video generation models. Code is also open-sourced.
∙ [2023-11] I am awarded the Google PhD Fellowship 2023
∙ [2023-11] Invited talk at Adobe Research on “Exploring Free Lunch in Diffusion U-Net”
∙ [2023-11] We released FreeU and its code
∙ [2023-11] We released Collaborative Diffusion (CVPR 2023) and its code
∙ [2023-11] We released ReVersion and its code
∙ [2023-10] Awarded Outstanding Reviewer for CVEU Workshop (ICCV 2023)
∙ [2023-02] One paper is accepted to CVPR 2023
∙ [2022-12] We are organizing Women in Computer Vision (WiCV) Workshop at CVPR 2023
∙ [2022-09] Awarded The Global Undergraduate Award Regional Winner (Asia)
∙ [2022-08] We are organizing SenseHuman Workshop at ECCV 2022
∙ [2022-08] Release CelebA-Dialog, a large-scale visual-language face dataset
∙ [2022-08] Start my journey at MMLab@NTU as a Ph.D. student
∙ [2022-06] Awarded Lee Kuan Yew Gold Medal (Top 1 in Undergraduate Cohort)
∙ [2021-07] One paper is accepted to ICCV 2021
∙ [2021-05] One paper is accepted to ICIP 2021

Education

Nanyang Technological University

Aug 2022 - Present
Ph.D. student at MMLab@NTU

Nanyang Technological University

Aug 2018 - May 2022
B.E. in Information Engineering & Media
CGPA: 5.00 / 5.00 (ranking: 1)

Publications

VBench: Comprehensive Benchmark Suite for Video Generative Models

Ziqi Huang*, Yinan He*, Jiashuo Yu*, Fan Zhang*, Chenyang Si, Yuming Jiang, Yuanhan Zhang, Tianxing Wu, Qingyang Jin, Nattapol Chanpaisit, Yaohui Wang, Xinyuan Chen, Limin Wang, Dahua Lin†, Yu Qiao†, Ziwei Liu†
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 (Spotlight)
Paper | Video | Code | Project Page | Demo

FreeU: Free Lunch in Diffusion U-Net

Chenyang Si, Ziqi Huang, Yuming Jiang, Ziwei Liu†
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 (Oral)
Paper | Video | Code | Project Page | Demo

Generative Networks

Ziwei Liu†, Shuai Yang, Yuming Jiang, Ziqi Huang
Handbook of Face Recognition, Third Edition, 2023
Digital Book

Talk-to-Edit: Fine-Grained 2D and 3D Facial Editing via Dialog

Yuming Jiang, Ziqi Huang, Tianxing Wu, Xingang Pan, Chen Change Loy, Ziwei Liu†
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023
PDF | Paper | Project Page

Collaborative Diffusion for Multi-Modal Face Generation and Editing

Ziqi Huang, Kelvin C.K. Chan, Yuming Jiang, Ziwei Liu†
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Paper | Video | Code | Project Page

Talk-to-Edit: Fine-Grained Facial Editing via Dialog

Yuming Jiang*, Ziqi Huang*, Xingang Pan, Chen Change Loy, Ziwei Liu†
IEEE/CVF International Conference on Computer Vision (ICCV), 2021
Paper | Video | Code | Project Page | Dataset

A Diagnostic Study of Visual Question Answering with Analogical Reasoning

Ziqi Huang, Hongyuan Zhu†, Ying Sun, Dongkyu Choi, Cheston Tan, Joo−Hwee Lim
IEEE International Conference on Image Processing (ICIP), 2021
PDF | Paper | Video

Preprints

FreeInit : Bridging Initialization Gap in Video Diffusion Models

Tianxing Wu, Chenyang Si, Yuming Jiang, Ziqi Huang, Ziwei Liu†
arXiv Preprint, 2023
Paper | Video | Code | Project Page | Demo

LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models

Yaohui Wang*, Xinyuan Chen*, Xin Ma*, Shangchen Zhou, Ziqi Huang, Yi Wang, Ceuyuan Yang, Yinan He, Jiashuo Yu, Peiqing Yang, Yuwei Guo, Tianxing Wu, Chenyang Si, Yuming Jiang, Cunjian Chen, Chen Change Loy, Bo Dai, Dahua Lin†, Yu Qiao†, Ziwei Liu†
arXiv Preprint, 2023 Paper | Project Page | Code

ReVersion: Diffusion-Based Relation Inversion from Images

Ziqi Huang*, Tianxing Wu*, Yuming Jiang, Kelvin C.K. Chan, Ziwei Liu†
arXiv Preprint, 2023
Paper | Video | Code | Project Page | Dataset | Demo

Awards

∙ (2023) Google PhD Fellowship
∙ (2023) Outstanding Reviewer, CVEU Workshop, ICCV 2023
∙ (2022) The Global Undergraduate Award Regional Winner (Asia)
∙ (2022) Lee Kuan Yew Gold Medal (Top 1 in Undergraduate Cohort)
∙ (2020 & 2021) NTU President Research Scholar
∙ (2019 & 2022) Dean’s List (School of Electrical and Electronic Engineering)
∙ (2018) NTU Science and Engineering Undergraduate Scholarship

Talk

∙ [2023-10] Invited talk at Adobe Research on “Exploring Free Lunch in Diffusion U-Net”, Slides, Video
∙ [2023-06] Invited talk at Zhi Dongxi (智东西) on “Collaborative Diffusion and Human-Machine Collaborative AIGC”, Slides

Professional Service

Workshops Organizer:
∙ CVPR 2024 - General Chair - Women in Computer Vision (WiCV) Workshop, Website
∙ CVPR 2023 - Organizer - Women in Computer Vision (WiCV) Workshop, Website, Report, Video
∙ ECCV 2022 - Organizer - SenseHuman: Sensing, Understanding and Synthesizing Humans, Website, Video

Talks Organizer:
∙ The AI Talks - keeping up with the latest advances in AI

Reviewer:
∙ Conference Reviewer: CVPR, ICCV, ICLR, ICIP
∙ Journal Reviewer: IJCV, IET CV
∙ Workshop Reviewer: ICCV 2023 CVEU Workshop (Outstanding Reviewer), CVPR 2023 WiCV Workshop

Teaching

∙ Teaching Assistant: SC2001/CE2101/CZ2101 Algorithm Design & Analysis, NTU, 2024 Spring ∙ Teaching Assistant: SC2001/CE2101/CZ2101 Algorithm Design & Analysis, NTU, 2023 Spring