Feiran Wang

Hi, I'm Feiran, a third-year PhD student in computer vision at Illinois Tech, advised by Professor Yan Yan. I'm currently visiting University of Michigan, Ann Arbor.

My research focuses on integrating the physical world into the digital domain and creating real-world impact, with particular emphasis on 3D reconstruction, vision foundation models, medical imaging, and generative AI.

I hold a M.S. from University of Illinois Urbana-Champaign, advised by Professor David Forsyth, and a B.S. from Shanghai University, advised by Professor Xiaoqiang Li. Previously, I had academic visits at the University of Toronto and University of Illinois Chicago.

Email  /  CV  /  Github  /  Linkedin  /  Scholar

🔥 News

• 📢 Actively looking for summer internship 2026! View my Resume
• 2026.02: One paper, CIF, is accepted to CVPR 2026 🎉
• 2026.01: One first-author paper, CogniMap3D, is accepted to ICLR 2026 🎉
• 2026.01: Started my Visiting Scholar position at the University of Michigan, Ann Arbor.
• 2026.01: Our research on long-term memory reconstruction, CogniMap3D, is available on arXiv.
• 2025.12: Code for X-Field is now publicly available.
• 2025.09: One first-author paper, X-Field, is accepted to NeurIPS 2025 as Spotlight (top 3%) 🎉
• 2025.03: Our work on 3D medical image generation, ZECO, is accepted to MVA 2025 (Oral).

Publication

CIF formulates a continuous probabilistic field over object existence and identity in space-time, enabling consistent instance representations across views for dynamic scene understanding.

We revisit and observe that RayMap-based predictions exhibit inherent static scene bias and propose RayMap3R, a training free streaming framework for dynamic scene reconstruction.

We present CogniMap3D, a bioinspired framework that maintains a persistent memory bank of static scenes, enabling efficient spatial knowledge storage and rapid retrieval.

Rooted in the X-ray imaging process, X-Field presents a representation specifically for high-quality X-ray Novel View Synthesis and CT Reconstruction.

To mitigate of medical data scarcity, ZECO synthesizes high-quality 3D MRI images across various modalities, conditioned on segmentation masks.

Point Clouds captured by Lidar are often colorless, PCCN-RE enables high-quality colorization with a relevance embedding module on Conditional GAN.

Scientific Project

Understanding morphology and distribution of neurons remains a significant challenge in modern neuroscience. We aim to develop a unified framework for sparse-to-dense neural generation and unsupervised segmentation, providing deeper insights into neural activity and connectivity.

Article

Award

Design from Jon Barron's web