Yunfan Ye

Yunfan Ye (叶云帆) is an Assistant Professor in School of Design, Hunan University (HNU), China. I earned my Ph.D. degree in December 2023 in National University of Defense Technology, under the supervision of Prof. Zhiping Cai and Prof. Kai Xu in iGrape Lab. I got my Master's degree in Computer Science in 2019 from Stevens Institute of Technology, and Bachelor's degree in Computer Science in 2017 from Xiamen University, China.

Email  /  Google Scholar  /  Github

profile photo
Teaching

Intelligent Design Method (智能设计方法) [Code]

Research

My research interest mainly include computer vision and graphics, intelligent design and their applications, especially edge detection, neural radiance field. The representative papers are highlighted.

DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection
Yunfan Ye*, Kai Xu*, Yuhang Huang†, Renjiao Yi, Zhiping Cai
AAAI, 2024
[Paper] [Code] [News]

Limited by the encoder-decoder architecture, learning-based edge detectors usually have difficulty predicting edge maps that satisfy both correctness and crispness. With the recent success of the diffusion probabilistic model (DPM), we found it is especially suitable for accurate and crisp edge detection...

NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction from Multi-view Images
Yunfan Ye, Renjiao Yi, Zhirui Gao, Chenyang Zhu, Zhiping Cai, Kai Xu†
CVPR, 2023
[Paper] [Code] [Project Page]

We study the problem of reconstructing 3D feature curves of an object from a set of calibrated multi-view images. To do so, we learn a neural implicit field representing the density distribution of 3D edges which we refer to as Neural Edge Field (NEF). Inspired by NeRF...

Delving into Crispness: Guided Label Refinement for Crisp Edge Detection
Yunfan Ye, Renjiao Yi, Zhirui Gao, Zhiping Cai†, Kai Xu†
IEEE TIP, 2023
[Paper] [Code]

Learning-based edge detection usually suffers from predicting thick edges. Through extensive quantitative study with a new edge crispness measure, we find that noisy human-labeled edges are the main cause of thick predictions...

STEdge: Self-Training Edge Detection With Multilayer Teaching and Regularization
Yunfan Ye*, Renjiao Yi*, Zhiping Cai†, Kai Xu†
IEEE TNNLS, 2023
[Paper] [Code]

Learning-based edge detection has hereunto been strongly supervised with pixel-wise annotations which are tedious to obtain manually. We study the problem of self-training edge detection, leveraging the untapped wealth of large-scale unlabeled image datasets...

Fixing the Double Agent Vulnerability of Deep Watermarking: A Patch-Level Solution against Artwork Plagiarism
Yuanjing Luo*, Tongqing Zhou*, Shenglan Cui, Yunfan Ye, Fang Liu†, Zhiping Cai
IEEE TCSVT, 2023
[Paper] [Code]

Increasing artwork plagiarism incidents stresses the urgent need for proper copyright protection on behalf of the creators. The latest development in this context focuses on embedding watermarks via deep encoder-decoder networks...

Learning Accurate Template Matching with Differentiable Coarse-to-Fine Correspondence Refinement
Zhirui Gao, Renjiao Yi, Zheng Qin, Yunfan Ye, Chenyang Zhu, Kai Xu†

Computational Visual Media Journal (CVMJ)
[Paper] [Code]

Template matching is a fundamental task in computer vision and has been studied for decades. It plays an essential role in manufacturing industry...

Image Captioning for Cultural Artworks: a Case Study on Ceramics
Baoying Zheng, Fang Liu†, Mohan Zhang, Tongqing Zhou, Shenglan Cui, Yunfan Ye, Yeting Guo

Multimedia System
[Paper]

When viewing ancient artworks, people try to build connections with them to ‘read’ the correct messages from the past. A proper descriptive caption is essential for viewers...

Source code from Jon Barron's website