Aaron Inbum Park

I am an M.S. student at the University of Michigan, advised by Prof. Andrew Owens.

I obtained my bachelor's degree in Electrical and Computer Engineering from Seoul National University, where I was fortunate to work under Prof. Jungdam Won, Prof. Se Young Chun, and Prof. Young Min Kim.

My research interests lie in the intersection of computer vision and graphics, especially leveraging generative models for compositional image/shape generation or motion reconstruction.

**I am actively looking for PhD openings starting in Fall 2025**

Email / CV / Google Scholar / LinkedIn / Twitter

Publications

	Factorized Diffusion: Perceptual Illusions by Noise Decomposition Daniel Geng, Inbum Park, Andrew Owens European Conference on Computer Vision (ECCV), 2024 Another zero-shot framework that is able to generate various perceptual illusions like hybrid images, by controlling linear components of an image, with connections to prior work in compositional generation and inverse problems. paper / arXiv / project
	Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models Daniel Geng, Inbum Park, Andrew Owens Conference on Computer Vision and Pattern Recognition (CVPR), 2024 (Oral) A simple, zero-shot method for generating multi-view optical illusions, which are images that change their appearance or identity upon a transformation. paper / arXiv / project
	On the Robustness of Normalizing Flows for Inverse Problems in Imaging Seongmin Hong, Inbum Park, Se Young Chun International Conference on Computer Vision (ICCV), 2023 A study on erroneous images occasionally generated from flow-based models for inverse problems in imaging. paper / arXiv / project
	Text2PointCloud: Text-Driven Stylization for Sparse PointCloud Inwoo Hwang, Hyeonwoo Kim, Donggeun Lim, Inbum Park, Young Min Kim Eurographics (Short Papers), 2023 A framework that stylizes and upsamples an uncolored, sparse pointcloud given a text description to render a high-quality 3D output. paper / video
	Probabilistic Implicit Scene Completion Dongsu Zhang, Changwoon Choi, Inbum Park, Young Min Kim International Conference on Learning Representations (ICLR), 2022 (Spotlight) A probabilistic approach to shape completion and scene reconstruction using 3D implicit representations. paper / arXiv / code

Service

• Reviewer: CVPR 2025

Misc

I am immersed in the choreography scene and also love learning languages, including French and Italian.

Source code credit to Dr. Jon Barron
Last updated March 2025