Aaron Inbum Park

I am a first-year CS Ph.D. student at the University of Maryland.

Previously, I graduated with an M.S. at the University of Michigan, where I was fortunate to be advised by Prof. Andrew Owens and closely worked with Daniel Geng and Connelly Barnes. During my bachelor's degree at Seoul National University, I worked with 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 synthesis.

University of Maryland
Ph.D. in CS

2025 - Present

University of Michigan
M.S. in ECE

2023 - 2025

Seoul National University
B.S. in ECE

2017 - 2023

Research

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.

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

Coming Soon

Service

Contact

Designed with Cursor Pro by myself
Last updated Sep 2025