Renhe Zhang

I am a Ph.D. student in Computer Science at East China Normal University (ECNU), advised by Prof. Lizhuang Ma in the Digital Media & Computer Vision Laboratory (DMCV). I am also co-supervised by Prof. Xin Tan.

Prior to starting my Ph.D. studies, I completed my master’s degree under the supervision of Prof. Qian Zhang at ECNU.

Email  /  Google Scholar  /  Github

Research

• My research interests involve computer vision and deep learning.
• Currently, I focus on foundation models for 3D vision, including spatial reasoning, 3D reconstruction, and 3D Gaussian Splatting.
• Previously, I also worked on 2D image segmentation, especially for remote sensing images.

Publications

3D Scene Understanding

• S2GS: Streaming Semantic Gaussian Splatting for Online Scene Understanding and Reconstruction. International Conference On Machine Learning (ICML, CCF-A), 2026.
  Renhe Zhang, Yuyang Tan, Jingyu Gong, Zhizhong Zhang, Lizhuang Ma, Yuan Xie, Xin Tan.

Remote Sensing Image Segmentation

• LSRFormer: Efficient Transformer Supply Convolutional Neural Networks With Global Information for Aerial Image Segmentation. IEEE Transactions on Geoscience and Remote Sensing (TGRS, CAS Q1 Top, JCR Q1, IF 8.2), 2024.
  Renhe Zhang, Qian Zhang, Guixu Zhang.
• DSAT-Net: Dual Spatial Attention Transformer for Building Extraction From Aerial Images. IEEE Geoscience and Remote Sensing Letters (GRSL, CAS Q2, JCR Q1, IF 5.1), 2023.
  Renhe Zhang, Zhechun Wan, Qian Zhang, Guixu Zhang.
• SDSC-UNet: Dual Skip Connection ViT-Based U-Shaped Model for Building Extraction. IEEE Geoscience and Remote Sensing Letters (GRSL, CAS Q2, JCR Q1, IF 5.1), 2023.
  Renhe Zhang, Qian Zhang, Guixu Zhang.

This homepage's source code is from Jon Barron's website.