官善琰

Researcher | vivo Imaging Department

Email: guanshanyan@vivo.com

Address: vivo Shanghai R&D Center, Pudong New Area, Shanghai

长期招收实习生，少量应届校招名额。研究方向：视频模型后训练、高效图像生成/编辑、世界模型等。有意者请并附上简历。

Profile Photo

About Me

I am Shanyan Guan (官善琰), a researcher specializing in computer vision and artificial intelligence. Currently, I work at vivo Imaging Department, focusing on AI Photography R&D. I received my Ph.D. from Shanghai Jiao Tong University under the supervision of Prof. Xiaokang Yang and Prof. Yunbo Wang, and my B.S. from Xidian University in 2017.

Industry Experience: I have gained valuable experience through internships at leading technology companies including Tencent XR, SenseTime, Tencent YouTu Lab, and miHoYo, where I applied computer vision and AI technologies across diverse domains including gaming, autonomous systems, and mobile applications.

Research Focus: My research spans both academic and industrial applications. During my Ph.D., I focused on machine understanding of real-world dynamics and motion analysis. Currently, I concentrate on high-resolution image generation, video synthesis, and world models for mobile camera systems.

Publications (* Co-first author, † Project Lead)

Describe, Don't Dictate: Semantic Image Editing with Natural Language Intent

En Ci*, Shanyan Guan*, Yanhao Ge, Yilin Zhang, Wei Li, Zhenyu Zhang, Jian Yang, Ying Tai

ICCV 2025

[Paper] [知乎]

PostEdit: Posterior Sampling for Efficient Zero-Shot Image Editing

Feng Tian, Yixuan Li, Yichao Yan, Shanyan Guan, Yanhao Ge, Xiaokang Yang

ICLR 2025

[Paper] [Code]

NeuMA: Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics

Junyi Cao, Shanyan Guan†, Yanhao Ge, Wei Li, Xiaokang Yang, Chao Ma

NeurIPS 2024

[Paper] [Code] [Project Page] [知乎]

HybridBooth: Hybrid Prompt Inversion for Efficient Subject-Driven Generation

Shanyan Guan*, Yanhao Ge*, Ying Tai, Jian Yang, Wei Li, Mingyu You

ECCV 2024

[Paper] [Project Page]

CageNeRF: Cage-based Neural Radiance Field for Generalized 3D Deformation and Animation

Yicong Peng, Yichao Yan, Shengqi Liu, Yuhao Cheng, Shanyan Guan, Bowen Pan, Guangtao Zhai, Xiaokang Yang

NeurIPS 2022

[Paper] [Project Page] [Code] [知乎]

Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation

Shanyan Guan, Jingwei Xu, Michelle Z He, Yunbo Wang, Bingbing Ni, Xiaokang Yang

T-PAMI 2022

[Paper] [Project Page] [Code]

PTSEFormer: Progressive Temporal-Spatial Enhanced Transformer Towards Video Object Detection

Han Wang, Jun Tang, Xiaodong Liu, Shanyan Guan, Rong Xie, Li Song

ECCV 2022

[Paper] [Code]

NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields

Shanyan Guan, Huayu Deng, Yunbo Wang, Xiaokang Yang

ICML 2022

[Paper] [Project Page] [Code] [上海交大新闻网]

Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction

Shanyan Guan*, Jingwei Xu*, Yunbo Wang, Bingbing Ni, Xiaokang Yang

CVPR 2021

[Paper] [Project Page] [Code]

Collaborative Learning for Faster StyleGAN Embedding

Shanyan Guan, Ying Tai, Bingbing Ni, Feida Zhu, Feiyue Huang, Xiaokang Yang

arXiv preprint, 2019

[Paper]

Human Action Transfer Based on 3D Model Reconstruction

Shanyan Guan*, Shuo Wen*, Dexin Yang*, Bingbing Ni, Wendong Zhang, Jun Tang, Xiaokang Yang

AAAI'19 Oral

[Paper]

Talks & Presentations

Next-Gen Camera Systems: Instilling Intuitive Imagination in Smartphones

[Event Page]

GAMES Webinar 337: Next-Gen Camera System: Instilling Intuitive Imagination in Smartphones

[Video]

基于视觉的领域泛化和物理运动推断

[Course]

基于视觉的物理规律反演

[Course]