Chaoran Feng

Education

• [2020-2024] 🎉 I received my B.E. degree from Dalian University of Technology, awarded the Outstanding Graduate (Top 3%), ranking 1^st/85 for three years (2021-2023).
• [2024-Now] 💪 I'm pursuing my M.S. degree in ECE, PKU, supervised by Prof. Li Yuan and Prof. Yonghong Tian.

Biography

I am a first-year M.S. student in ECE at Peking University, holding a B.E. degree from Dalian University of Technology. During my undergraduate studies, I achieved a GPA of 3.8/4.0, ranking 1^st/85 in both major and overall scores.

📌 My research interests focus on 3D Vision, Neuromorphic Vision, and Generative Model.

News

• [2025-03] 🔥 We release "NeuralGS", a novel framework that effectively adopts the neural field representation to encode the attributes of 3D Gaussians with multiple tiny MLPs.
• [2025-01] 🔥 We release "AE-NeRF", a novel framework for 3D reconstruction using event streams under noisy poses and in unbounded larger scenes.
• [2024-12] Two papers accepted by AAAI 2025.
• [2024-05] 🔥 We release "EvaGaussians", a first approach that reconstruct sharp static 3D scenes with sparse RGB frames and event streams.
• [2023-09] One papers accepted by NeurIPS 2023.

Selected Projects

* Equal Contribution    # Project Lead

♠ 3D Reconstruction & Generative Model

• 🔥 Cycle3D:High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle
  Zhenyu Tang*, Junwu Zhang*, Xinhua Cheng, Wangbo Yu, Chaoran Feng, Yatian Pang, Bin Lin, Li Yuan†
  The project is about 3d generation used to generation-reconstruction cycle for the unified diffusion process.
  AAAI 2025
  
  [Paper] [Code 🌟200+]

• 🔥 NeuralGS:Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations
  Zhenyu Tang*, Chaoran Feng*, Xinhua Cheng, Wangbo Yu, Junwu Zhang, Yuan Liu†, Xiaoxiao Long, Wenping Wang, Li Yuan†

  A novel framework using neural fields to encode 3D Gaussians with compact MLPs for large-scale scenes.

  Arxiv 2025
  

  [Paper] [Code 🌟150+]

• D²GS: Deblurring Deformable 3D Gaussian Splatting for Motion-Blurred Causal Videos
  Chaoran Feng, Jianbin Zhao, Wangbo Yu, Zhenyu Tang, Yuchen Li, Li Yuan†, and Yonghong Tian†

  A novel framework to reconstruct High-quality 4D scenes from blurry videos.

  Notes: Paper is under review by T-CSVT!
  

  [Paper]

• NOFA++: Tuning-free NeRF-based One-shot Facial Avatar Reconstruction
  Wangbo Yu, Chaoran Feng, Yanbo Fan†, Yong Zhang, Xuan Wang, Fei Yin, Yunpeng Bai, Baoyuan Wu, Yan-Pei Cao, Li Yuan†, and Yonghong Tian†
  One-shot 3D facial avatar reconstruction with high fidelity and dynamic reenactment from a single image.
  Notes: Paper is under review by T-PAMI!
  
  [Paper]

♠ Neuromorphic Vision

• E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event Cameras
  Chaoran Feng, Zhenyu Tang, Wangbo Yu, Yatian Pang, Yian Zhao, Jianbin Zhao, Li Yuan†, Yonghong Tian†

  The project is about high-fidelity 4d reconstruction with Multi-view event stream in fast-moving setting..

  Notes: Paper is under review by ACMMM 2025!
  

  [Paper]

• AE-NeRF:Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scenes
  Chaoran Feng, Wangbo Yu, Xinhua Cheng, Zhenyu Tang, Junwu Zhang, Li Yuan†, Yonghong Tian†

  The project is about 3d reconstruction with event stream in noisy poses and unbounded larger scenes.

  AAAI 2025
  

  [Paper] [Code]

• EvaGaussians:Event Assisted Gaussian Splatting from Blurry Images
  Wangbo Yu*, Chaoran Feng*, Jiye Tang, Jiashu Yang, Zhenyu Tang, Xu Jia, Yuchao Yang, Li Yuan†, Yonghong Tian†

  The project is about 3d reconstruction with event stream in noisy poses and unbounded larger scenes.

  Arxiv 2024
  

  [Paper] [Code 🌟50+]

• EICIL:Joint Excitatory Inhibitory Cycle Iteration Learning for Deep Spiking Neural Networks
  Zihang Shao, Xuanye Fang, Yaxin Li, Chaoran Feng, Jiangrong Shen, Qi Xu†

  The project is about 3d reconstruction with event stream in noisy poses and unbounded larger scenes.

  NeurIPS 2023
  

  [Paper]

Award

• [2024-06] Outstanding Graduate, Dalian University of Technology (Top 3%)
• [2023-05] 1^st Prize in the China Robotics and Artificial Intelligence Competition (Ranked 1^st/100+)
• [2022-10] Qubochuan Scholarship, highest scholarship of DUT, awarded to only 10 recipients each year
• [2021,2022,2023] Nation Scholarship, three times, Dalian University of Technology
• [2021,2022,2023] Academic Excellence Scholarship (First Class) (Ranked 1^st/85), Dalian University of Technology

Professional Activities

• Conference Reviewer: ICLR[25], CVPR[25], ICCV[25], NeurIPS[24-25], AAAI[25], IJCAI[25], ACM MM[25];
• Jounal Reviewer: TCSVT;