Junho Park

I'm a Ph.D. student in the Department of Computing at Imperial College London, advised by Dr. Rolandos Alexandros Potamias.

My research lies at the intersection of 3D vision, generative AI, and embodied intelligence. I am interested in developing foundation models that bridge human-centered perception and robotic manipulation, enabling robots to learn from human interactions and generalize across objects, tasks, and environments.

Previously, I was a Research Engineer at LG Electronics. At LG Electronics, my team collaborated with Apple to deploy lightweight vision AI models in smart home products and develop automated pipelines for edge-case generation and model training. I also developed vision AI models for LG's Physical AI initiative with NVIDIA, supporting robotic data collection and embodied AI development. Additionally, I contributed to a multi-task on-device vision foundation model showcased at CES 2025.

I received my M.S. in Electronic Engineering under the supervision of Prof. Suk-Ju Kang and my B.S. with double majors in Mathematics and Electronic Engineering, both from Sogang University. During my master's studies, I conducted research spanning 3D vision, diffusion models, and large language models (LLMs).

Email  /  CV  /  Scholar  /  LinkedIn  /  GitHub

News

Publications

We introduce EgoWorld, a novel two-stage framework that reconstructs egocentric view from rich exocentric observations, including depth maps, 3D hand poses, and textual descriptions.

We introduce a text-guided object replacement framework, Replace-in-Ego, which integrates a vision-language model (VLM)-based segmentation model with a diffusion transformer (DiT).

We introduce GenEgo, a novel two-stage framework that generates an egocentric view from multimodal exocentric observations, including projected point clouds, 3D hand poses, and textual descriptions.

Programmable-Room interactively creates and edits textured 3D meshes given user-specified language instructions. Using pre-defined modules, it translates the instruction into python codes which is executed in an order.

We propose a novel method, AttentionHand, for text-driven controllable hand image generation. The performance of 3D hand reconstruction was improved by additionally training with hand images generated by AttentionHand.

We introduce a novel framework, Interactive Room Programmer (IRP), which allows users to conveniently create and modify 3D indoor scenes using natural language.

We propose a new interacting hand pose transfer model, IHPT, which is a diffusion-based approach designed to transfer hand poses between source and target images.

We present a new SEM dataset and a two-stage deep learning method (including SEMixup and SEM-SPNet) that achieve state-of-the-art performance in SEM image restoration and structure prediction under diverse conditions.

We propose a novel framework, HANDiffusion, which generates new 3D hand datasets with in-the-wild scenes.

We propose a novel gaze tracking method for large screens using a symmetric angle amplifying function and center gravity correction to improve accuracy without personalized calibration, with applications in autonomous vehicles.

Affiliation

Collaboration

Website template from Jon Barron.