Wonbong Jang

Hello! My name is Wonbong - Won is also fine with me. I am a final-year PhD student in CS at University College London, primarily supervised by Prof Lourdes Agapito. During my PhD, I've worked on 3D Computer Vision, focusing on generating 3D implicit representations from images. I've played with Transformers for sometime, and nowadays, I am interested in Diffusion Models (especially for 3D implicit representation where we do not have the ground-truth). Happy to talk about these topics.

Email  /  Google Scholar  /  X  /  LinkedIn /  Github

profile photo

Papers
NViST: In the wild New View Synthesis from a Single Image with Transformers
Wonbong Jang, Lourdes Agapito
CVPR, 2024
project page / arXiv / code / paper

NViST turns in-the-wild sinlge images into implicit 3D functions with a single pass using Transformers.
Extending CodeNeRF to multiple real world scenes, Feed-forward model, Transformers
CodeNeRF: Disentangled Neural Radiance FIelds for Object Categories
Wonbong Jang, Lourdes Agapito
ICCV, 2021
project page / arXiv / code

Disentangled NeRF, Conditional NeRF, Generalizing NeRF

Books and Movies

The below list contains some books and movies that I like and currently read/watch -