Rundong Luo

Rundong Luo

I’m a third-year CS PhD student at Cornell University, working with Prof. Wei-Chiu Ma and Prof. Noah Snavely. My research interests focus on 3D vision and video generative models, where I aim to develop systems that are capable of creating or reconstructing highly controllable and photorealistic environments.

I was a research intern at Luma AI, Microsoft Research Asia, and an undergraduate visiting researcher (UGVR) at Stanford University. I obtained my Bachelor’s degree in Computer Science (summa cum laude) from the Turing class, Peking University. During my journey, I am honored to be advised by Prof. Jiajun Wu, Prof. Jiaying Liu, and Prof. Yisen Wang.

You may find my CV here: Rundong’s Curriculum Vitae. Feel free to reach out to me via email or Wechat if you have any questions or just want to chat!

Publications

All publications

* Equal contribution † Equal advising

2026

  1. SceneRig: An Agentic System for Simulation-Ready 3D Scene Reconstruction from Single Images
    Rundong Luo, Yunong Liu*, Di Cao*, Matthew Tancik, Shyamal Buch, Colton Stearns, and Wenqi Xian
    arXiv, 2026
    Oral Presentation at CoRL 2026 PhysWM Workshop
  2. SMG: Semantic Motion Graph for Monocular Dynamic Gaussian Splatting
    In European Conference on Computer Vision (ECCV), 2026
  3. Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language Models
    arXiv, 2026
  4. Seeing Fast and Slow: Learning the Flow of Time in Videos
    In European Conference on Computer Vision (ECCV), 2026
  5. ShadowDraw: From Any Object to Shadow-Drawing Compositional Art
    Rundong Luo, Noah Snavely, and Wei-Chiu Ma
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

2025

  1. Beyond the Frame: Generating 360° Panoramic Videos from Perspective Videos
    In IEEE/CVF International Conference on Computer Vision (ICCV), 2025
    Oral Presentation at BinEgo-360° Workshop
  2. PhysPart: Physically Plausible Part Completion for Interactable Objects
    Rundong Luo*, Haoran Geng*, Congyue Deng, Puhao Li, Zan Wang, Baoxiong Jia, Leonidas Guidbas, and Siyuan Huang
    In International Conference on Robotics and Automation (ICRA), 2025
  3. Unsupervised Discovery of Object-Centric Neural Fields
    Rundong Luo*, Hong-Xing Yu*, and Jiajun Wu
    Transactions on Machine Learning Research (TMLR), 2025

2024

  1. Unsupervised Illumination Adaptation for Low-Light Vision
    Wenjing Wang*, Rundong Luo*, Wenhan Yang, and Jiaying Liu
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024

2023

  1. Similarity Min-Max: Zero-Shot Day-Night Domain Adaptation
    Rundong Luo, Wenjing Wang, Wenhan Yang, and Jiaying Liu
    In IEEE/CVF International Conference on Computer Vision (ICCV), 2023
    Oral Presentation at Main Conference
  2. Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning
    Rundong Luo*, Yifei Wang*, and Yisen Wang
    In International Conference on Learning Representations (ICLR), 2023

Academic services

Workshop Organizer
SynData4CV @ CVPR 2025-2026
Conference Reviewer
CVPR 2024-2026, NeurIPS 2024-2026, WACV 2025, ICLR 2025-2026, ICML 2025-2026, ICCV 2025, ECCV 2026
Journal Reviewer
TIP, TCSVT, TOMM, TPAMI
Teaching Assistant
Computer Vision (CS5670 @ Cornell, Spring 2026); 3D Vision (CS6672 @ Cornell, Fall 2024); Practice of Programming in C&C++ (04831750 @ PKU, Spring 2023)

Selected honors and awards

2024
Outstanding Undergraduate Thesis (Beijing Municipal, 34/4000+ in PKU), PDF
2024
Excellent Graduate (Beijing Municipal, 190/4000+ in PKU)
2023
Sensetime Scholarship (30 AI undergraduates per year Nationwide)
2023
Chinese National Scholarship (awarded to top 0.2% undergraduates in China)
2020
Ranked 4th in National Examination for University Admission in Shanghai (aka Gaokao)