Xinghui Li

Xinghui Li - 李星辉

Researcher at ByteDance (Intelligent Creation Lab) | M.S. of Tsinghua University

Email
Generative Models 3D Reconstruction Computer Vision

Biography

I am currently a researcher at ByteDance (Intelligent Creation Lab), where I am working on the task of Video/Image Generation and AIGC.

Before that, I obtained my M.S. at Tsinghua University in 2024 and B.Eng at NUAA in 2021 (Rank 1/331).

If you are interested in working with me, please feel free to contact me at li-xh21@tsinghua.org.cn.

Selected Online Projects

360度旋转

Orbit360 💃

Video Effects in Douyin & CapCut

DreamID

DreamID 👑

AI Photo in Jimeng

AI Photo

Personalized AI Image 👸

AI Image in Douyin

shandian

Flash ⚡️

Video Effects in CapCut

animal

Animal Transformation 🐻

Video Effects in CapCut

melt

Melt 🫠

Video Effects in CapCut

Industrial Experience

ByteDance

Intelligent Creation Lab

Sep. 2023 - Present, Intelligent Creation Lab, Beijing, China

Topic: Image/Video Generation

Tencent

IEG

May. 2023 - Sep. 2023, IEG, Shenzhen, China

Topic: 3D Generation

DJI

Zhuoyu Technology

Feb. 2023 - May. 2023, ZYT, Shenzhen, China

Topic: 3D Reconstruction

Huawei

2012 Lab

Jun. 2022 - Feb. 2023, 2012 Lab, Shenzhen, China

Topic: 3D Reconstruction

Casia

Institute of Automation

Dec. 2021 - Jun. 2022, Beijing, China

Topic: 3D Reconstruction

Selected Publications

(* denotes equal contribution, ✝ denotes corresponding author.)

OmniInsert

OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models

Jinshu Chen*, Xinghui Li*✝, Baixu*, Tianxiang Ma, Pengze Zhang, Zhuowei Chen, Gen Li, Lijie Liu, Songtao Zhao✝, Bingchuan Li, Qian HE

Under Review

Paper Project Code
Phantom-Data

Phantom-Data: Towards a General Subject-Consistent Video Generation Dataset

Zhuowei Chen*, Bingchuan Li*✝, Tianxiang Ma*, Lijie Liu*, Mingcong Liu, Yi Zhang, Gen Li, Xinghui Li, Siyu Zhou, Qian He, Xinglong Wu

Under Review

Paper Project Code
Anydressing

AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models

Xinghui Li, Qichao Sun, Pengze Zhang, Fulong Ye, Zhichao Liao, Wanquan Feng✝, Songtao Zhao✝, Qian He

CVPR 2025

Paper Project Code
GaussianRoom

GaussianRoom: Improving 3D Gaussian Splatting with SDF Guidance and Monocular Cues for Indoor Scene Reconstruction

Haodong Xiang*, Xinghui Li*, Kai Cheng*, Xiansong Lai, Wanting Zhang, Zhichao Liao, Long Zeng✝, Xueping Liu✝

ICRA 2025

Paper Project Code
2DGS-Room

2DGS-Room: Seed-Guided 2D Gaussian Splatting with Geometric Constrains for High-Fidelity Indoor Scene Reconstruction

Wanting Zhang, Haodong Xiang, Zhichao Liao, Xiansong Lai, Xinghui Li✝, Long Zeng✝

Under Review

Paper Project Code
DreamID

DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learning

Fulong Ye*, Miao Hua*, Pengze Zhang, Xinghui Li, Qichao Sun, Songtao Zhao✝, Qian He✝, Xinglong Wu

SIGGRAPH ASIA 2025

Paper Project App
DreamO

DreamO: A Unified Framework for Image Customization

Chong Mou, Yanze Wu✝, Wenxu Wu, Zinan Guo, Pengze Zhang, Yufeng Cheng, Yiming Luo, Fei Ding, Shiwen Zhang, Xinghui Li, Mengtian Li, Mingcong Liu, Yi Zhang, Shaojin Wu, Songtao Zhao, Jian Zhang, Qian He, Xinglong Wu

SIGGRAPH ASIA 2025

Paper Project Code
training-free

Training-Free Point Cloud Recognition Based on Geometric and Semantic Information Fusion

Yan Chen, Di Huang, Zhichao Liao, Xi Cheng, Xinghui Li, Long Zeng✝

ICASSP 2025

Paper Project Code
MSFormer

Freehand sketch generation from mechanical components

Zhichao Liao*, Fengyuan Piao✝, Di Huang*, Xinghui Li✝, Yue Ma, Pingfa Feng, Heming Fang*, Long Zeng✝

ACM-MM 2024

Paper Code Code
GenesisTex

GenesisTex: Adapting Image Denoising Diffusion to Texture Space

Chenjian Gao*, Boyan Jiang, Xinghui Li, Yingpeng Zhang*, Qian Yu✝

CVPR 2024

Paper Project
FD-NeuS

Fine-detailed Neural Indoor Scene Reconstruction using Multi-level Importance Sampling and Multi-view Consistency

Xinghui Li, Yuchen Ji, Xiansong Lai, Wanting Zhang, Long Zeng✝

ICIP 2024

Paper
Ea-NeuS

Edge-aware neural implicit surface reconstruction

Xinghui Li*, Yikang Ding*, Jia Guo✝, Xiansong Lai, Shihao Ren, Wensen Feng, Long Zeng✝

ICME 2023

Paper

Honors & Awards

  • Outstanding Graduates of NUAA (Top 1%)

    2021.06

  • National Encouragement Scholarship (Top 3%)

    2020.12

  • Merit Student of Jiangsu Province (Top 0.2%)

    2020.06

  • Top 100 Youth of NUAA (Top 0.1%)

    2020.05

  • National Scholarship (Top 1%)

    2019.12

Research Interests

Generative Models

Diffusion models, video editing, image generation

3D Reconstruction

NeRF, 3DGS, 2DGS

3D Generation

Texture generation