Karhan Kayan

I am a fourth-year Ph.D. candidate in computer science at Princeton University, advised by Jia Deng as a member of the Princeton Vision & Learning Lab. I mainly work on 3D vision and procedural generation.

E-Mail Google Scholar Twitter LinkedIn CV
Princeton365: A Diverse Dataset with Accurate Camera PoseICCV 2025

Karhan Kayan* Stamatis Alexandropoulos*, Rishabh Jain, Yiming Zuo, Erich Liang, Jia Deng (*equal contribution)

TL;DR: A large-scale and diverse SLAM/NVS benchmark with accurate camera pose enabled by a novel ground-truth collection method.

  arXiv project page   code
Infinigen Indoors: Photorealistic Indoor Scenes using Procedural GenerationCVPR 2024

Karhan Kayan*, Alexander Raistrick*, Lingjie Mei*, David Yan, Yiming Zuo, Beining Han, Hongyu Wen, Meenal Parakh, Stamatis Alexandropoulos, Lahav Lipson, Zeyu Ma, Jia Deng (*equal contribution)

TL;DR: A Blender-based procedural generator of photorealistic indoor scenes

  arXiv project page   code
Infinite photorealistic worlds using procedural generation CVPR 2023

Alexander Raistrick*, Lahav Lipson*, Zeyu Ma*, Lingjie Mei, Mingzhe Wang, Yiming Zuo, Karhan Kayan, Hongyu Wen, Beining Han, Yihan Wang, Alejandro Newell, Hei Law, Ankit Goyal, Kaiyu Yang, Jia Deng (*equal contribution)

TL;DR: Infinigen, a Blender-based procedural generator of photorealistic nature scenes.

  arXiv project page   code   video
Towards Foundation Models for 3D Vision: How Close Are We?

Karhan Kayan*, Yiming Zuo*, Maggie Wang, Kevin Jeon, Jia Deng, Thomas L. Griffiths (*equal contribution)

TL;DR: 2D VLMs cannot solve 3D tasks. Specialized models are not robust enough for 3D foundation models.

  arXiv   code

This website is based on Erich Brachmann's template, which is based on Jon Barron's template.