Ming Qian

I am a final-year PhD student in Wuhan University, co-supervised by Prof. Gui-Song Xia and Nan Xue.

Email / Google Scholar / Github

News

2026-03 The paper Sat3DGen is accepted by ICLR 2026, code and demo will be released at GitHub.

2026-02 The code of Sat2Density++ is released at GitHub.

2026-01 Sat2Density++ is accepted by T-PAMI.

2024-04 Two papers are accepted by CVPR 2024.

2023-07 Sat2Density is accepted by ICCV 2023.

2020-08 BGGAN is accepted by ECCVW 2020.

2020-07 We win Winner Award at the ECCV AIM 2020 Challenge on Rendering Realistic Bokeh with Congyu and Jiamin.

Research

I'm interested in 3D vision and image processing. Much of my research is about inferring the physical world and camera (shape, motion, color, light, bokeh, etc) from images.

	Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image Ming Qian, Zimin Xia, Changkun Liu, Shuailei Ma, Wen Wang, Zeran Ke, Bin Tan, Hang Zhang, Gui-Song Xia ICLR, 2026 paper / code & demo (coming soon) Sat3DGen is a feed-forward satellite-to-3D framework that learns a structured, view-consistent NeRF-style scene from 2D satellite/street-view supervision, enabling mesh export and large-area mesh generation, surround-view video rendering, semantic-map-to-3D synthesis, and single-image DSM estimation.
	Seeing through Satellite Images at Street Views (Sat2Density++) Ming Qian, Bin Tan, Qiuyu Wang, Xianwei Zheng, Hanjiang Xiong, Gui-Song Xia, Yujun Shen, Nan Xue T-PAMI, 2026 project page / arXiv / code The journal extension of Sat2Density, significantly improves the consistency and quality of generated street-view videos and images.
	Multi-View Attentive Contextualization for Multi-View 3D Object Detection Xianpeng Liu, Ce Zheng, Ming Qian, Nan Xue, Chen Chen, Zhebin Zhang, Chen Li, Tianfu Wu CVPR, 2024 arXiv
	Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs Ming Qian, Jincheng Xiong, Gui-Song Xia, Nan Xue, ICCV, 2023 project page / code / arXiv Sat2Density focuses on the geometric nature of generating high-quality ground street videos conditioned on satellite images learning from collections of satellite-ground image pairs.
	Depth and DOF Cues Make Better Defocus Blur Detection Yuxin Jin, Ming Qian, Jincheng Xiong, Nan Xue, Gui-Song Xia ICME, 2023 arXiv / Code / Paper D-DFFNet considers the physical mechanism of defocus blur and successfully distinguishes homogeneous regions. In addition, we propose a larger benchmark EBD that includes more DOF cases. The results of detection on multiple public test sets look great.
	BGGAN: Bokeh-Glass Generative Adversarial Network for Rendering Realistic Bokeh Ming Qian, Congyu Qiao, Jiamin Lin, Zhenyu Guo, Chenghua Li, Cong Leng, Jian Cheng ECCVW, 2020 arXiv / Code BGGAN lets us synthesis bokeh effect images from bokeh-less images end to end. Rank 1st in eccv AIM 2020 challenge .

Design and source code from Jon Barron's website