Zhanpeng Luo

I'm a rising senior student majoring in Computer Science at the University of Pittsburgh. I am now interested in data-driven method for 3D perception and generation.

Inspired by Croco, Dust3R and VGGt, I start to agree that for 3d vision's next 5 years, compression is the intelligence and visual compression is the spatial intelligence.

Email  /  CV  /  Scholar  /  Twitter  /  Github  /  LinkedIn

profile photo

Research
Instant4D: 4D Gaussian Splatting in Minutes
Zhanpeng Luo, Haoxi Ran Li Lu
In submission, 2025
project page / paper

With dense initialization form deep visual SLAM, we simplify the formulation and optmization of 4D Gaussian Splatting.

pySpatial: Generating 3D Visual Programs for Zero-Shot Spatial Reasoning
Zhanpeng Luo, Ce Zhang Silong Yong Yaqi Xie Katia P. Sycara
Preparing for ICLR 26, 2025

Introduce 3D recontruction to enhance VLM's spatial reasoning with an agentic framework.

Experience

  • Research Intern at RI, CMU, through the RISS program. June 25 - Present
  • Research Intern, supervised by Bernhard Kerbl. Aug 2024 - Oct 2024
  • Develop an iOS app Link.

Something I want to share at the end

Steal this website's from Jon Barron. I like his talk at 3DV 2025.