Ye Chen (陈烨)

Ye Chen (陈烨)

PhD student @ SJTU

Brief Bio

Hi, there! This is Ye Chen, a final-year PhD student advised by Prof. Bingbing Ni from School of SEIEE, Shanghai Jiao Tong University. Previously, I received Master and Bachelor degree from the same university with honor degrees. I have published several papers on leading journals and conferences, e.g., CVPR, ICCV, ECCV, and T-PAMI. My research interest lies in the intersection between Graphics and Computer Vision, especially exploring controllable representations for video world models.

Google Scholar / E-mail / Github

News

[2026/08] One paper (co-first author) on Controllable Video Generation is released!
[2026/07] Our team releases World Narrative Model for Efficient, Controllable Industrial-grade AI Drama Production!
[2026/06] One paper (co-first author) on SVG unsderstanding and evaluation is accepted to ECCV 2026!
[2025/12] One paper (co-first author) on 3D-aware image editing and animation is released!
[2025/10] One paper (first author) on video representation and editing is released!
[2025/07] Two papers on SVG Generation and 3D Animation are accepted to ACMMM 2025!
[2025/02] Two papers on Image Representation/Editing and Neural Fluid Simulation are accepted to CVPR 2025!
[2024/11] One paper on Realistic Decal Blending is accepted to AAAI 2025!
[2024/10] I am very honored to be awarded the National PhD Scholarship!
[2024/07] One paper on Stroke Based Rendering is accepted to ACMMM 2024!
[2024/02] Two papers on Image Vectorization and Vector Graphics Generation are accepted to CVPR 2024!
[2023/09] Start my PhD journey with Prof. Bingbing Ni!
[2023/07] One paper on Image Vectorization is accepted to ICCV 2023!
[2023/04] Journal version of SSC for unsupervised point cloud learning is publised in T-PAMI!
[2023/03] Obtain master degree with Shanghai Outstanding Graduates from SJTU!
[2021/07] One paper (SSC) on Self-Supervised Point Cloud Learning is accepted to ICCV 2021!

Selected Publications

UniMoCa: Unifying Motion and Camera Controls as Visual Proxies for Faithful Human Video Generation

Liming Tan*, Ye Chen*, Hao Zhang, Lirong Qian, Feifei Li, Bingbing Ni. (* equal contribution)
Preprint, Arxiv, 2026. [Paper]

World Narrative Model for Highly Controllable Video Generation: A Paradigm Shift from Pixel Sampling to Physical World Orchestration

Ye Chen, Xuanhong Chen, Bingbing Ni and the Team.
Preprint, Arxiv, 2026. [Paper]

SVGEval: A Vision-Grounded Framework for Perceptual-Quality Benchmarking and Evaluation in Text-to-SVG Generation

Yiming Wang*, Ye Chen*, Hanqi Chen, Bingbing Ni. (* equal contribution)
ECCV, 2026. [Paper]

ProxyImg: Towards Highly-Controllable Image Representation via Hierarchical Disentangled Proxy Embedding

Ye Chen*, Yupeng Zhu*, Xiongzhen Zhang, Zhewen Wan, Yingzhe Li, Wenjun Zhang, Bingbing Ni.
Preprint, Arxiv, 2026. [Paper]

3DProxyImg: Controllable 3D-Aware Animation Synthesis from Single Image via 2D-3D Aligned Proxy Embedding

Yupeng Zhu*, Xiongzhen Zhang*, Ye Chen*, Bingbing Ni. (* equal contribution)
Preprint, Arxiv, 2025. [Paper]

ProxyVideo: Vectorized Video Representation with Easy Editing via Hierarchical Spatio-Temporally Consistent Proxy Embedding

Ye Chen, Liming Tan, Yupeng Zhu, Yuanbin Wang, Bingbing Ni.
Preprint, Arxiv, 2025. [Paper]

SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generation

Hanqi Chen, Zhongyin Zhao, Ye Chen, Zhujin Liang, Bingbing Ni.
ACMMM, 2025. [Paper]

Easy-editable Image Vectorization with Multi-layer Multi-scale Distributed Visual Feature Embedding

Ye Chen, Zhangli Hu, Zhongyin Zhao, Yupeng Zhu, Yue Shi, Yuxuan Xiong, Bingbing Ni.
CVPR, 2025. [Paper]

AMR-Transformer: Enabling Efficient Long-range Interaction for Complex Neural Fluid Simulation

Zeyi Xu, Jinfan Liu, Kuangxu Chen, Ye Chen, Zhangli Hu, Bingbing Ni.
CVPR, 2025. [Paper]

Towards Artist-Like Painting Agents with Multi-Granularity Semantic Alignment

Zhangli Hu, Ye Chen, Zhongyin Zhao, Jinfan Liu, Bilian Ke, Bingbing Ni.
ACMMM, 2024. [Paper]

Towards High-fidelity Artistic Image Vectorization via Texture-Encapsulated Shape Parameterization

Ye Chen, Bingbing Ni, Jinfan Liu, Xiaoyang Huang, Xuanhong Chen.
CVPR, 2024. [Paper]

Vector Graphics Generation via Mutually Impulsed Dual-domain Diffusion

Zhongyin Zhao, Ye Chen, Zhangli Hu, Xuanhong Chen, Bingbing Ni.
CVPR, 2024. [Paper]

Editable Image Geometric Abstraction via Neural Primitive Assembly

Ye Chen, Bingbing Ni, Xuanhong Chen, Zhangli Hu.
ICCV, 2023. [Paper]

Inferring Fluid Dynamics via Inverse Rendering

Jinxian Liu*, Ye Chen*, Bingbing Ni, Jiyao Mao, Zhenbo Yu. (* equal contribution)
Preprint, Arxiv, 2023. [Paper]

Fast Fluid Simulation via Dynamic Multi-Scale Gridding

Jinxian Liu, Ye Chen, Bingbing Ni, Wei Ren, Zhenbo Yu, Xiaoyang Huang.
AAAI, 2023. [Paper]

Learning by Restoring Broken 3D Geometry

Jinxian Liu, Bingbing Ni, Ye Chen, Zhenbo Yu, Hang Wang.
T-PAMI, 2023. [Paper]

Joint Global and Dynamic Pseudo Labeling for Semi-Supervised Point Cloud Sequence Segmentation

Jinxian Liu, Ye Chen, Bingbing Ni, Zhenbo Yu.
T-CSVT, 2023. [Paper]

Shape self-correction for unsupervised point cloud understanding

Ye Chen, Jinxian Liu, Bingbing Ni, Hang Wang, Jiancheng Yang, Ning Liu, Teng Li, Qi Tian.
ICCV, 2021. [Paper]

Self-prediction for joint instance and semantic segmentation of point clouds

Jinxian Liu, Minghui Yu, Bingbing Ni, Ye Chen.
ECCV, 2020. [Paper]

Selected Honors

[2024] National PhD Scholarship (博士生国家奖学金).
[2023] Shanghai Outstanding Graduates (上海市优秀毕业生).
[2022] NRIEE Scholarship (中国电子科技集团莱斯奖学金).
[2020] Shanghai Jiao Tong University Outstanding Graduates.
[2016] Shanghai Jiao Tong University Zhiyuan Honor Class.
[2015] First Prize in the National High School Physics Competition.