Wonbong Jang / Won

Hello! My name is Wonbong — but you can also call me Won. I completed my PhD at University College London, supervised by Prof. Lourdes Agapito, and currently work as a Postdoctoral Researcher at Meta on the Monetization + GenAI team in London.

My research focuses on learning to understand and reconstruct 3D scenes from images. During my PhD, I worked on feed-forward 3D reconstruction (NeRF, Pointmaps) from single or few images, and applied Diffusion models to handle partial observations of the 3D world. At Meta, I continue applying generative models to 3D problems, including novel view synthesis and leveraging video diffusion models for 3D tasks. I've always been drawn to 3D computer vision for its mathematical foundations, and as a long-time fan of probabilistic models, it's exciting to see how elegant mathematics underpins modern image and video generation.

Before transitioning to 3D Computer Vision and Machine Learning, I had the privilege of working for the Korean government for six years. Outside of research, I enjoy exploring around the city (London and its outskirts), having an espresso, listening to podcasts, reading books, thinking of economy, and solving math problems. Feel free to get in touch with me if you want a chat!

Email  /  Google Scholar  /  X  /  LinkedIn  /  Threads

Kaleido pushes the idea of "3D perception is not a geometric problem, but a form of visual common sense" to novel view synthesis problem. It generates beautiful renderings and achieves per-scene optimization model with much fewer number of input images.

DT-NVS extends NViST by leveraging diffusion models, an approach well-suited for the inherently probabilistic nature of novel view synthesis in occluded regions. The method maintains consistency with the input image while generating diverse outputs for these unseen parts, as shown in the teaser figure with an occluded car. This research was completed during the final stages of my PhD studies and is available on arXiv.

DUSt3R generates 3D pointmaps from regular images without requiring camera poses. In practice, significant effort is put into camera calibration or deploying additional sensors to acquire point clouds. We present Pow3R, a single network capable of processing any subset of this auxiliary information. By incorporating priors, our method achieves more accurate and precise 3D reconstructions, multi-view depth estimation, and camera pose predictions. This approach opens new possibilities, such as processing images at native resolution and performing depth completion. Additionally, Pow3R generates pointmaps in two distinct coordinate systems, enabling the model to compute camera poses more quickly and accurately.

NViST turns in-the-wild single images into implicit 3D functions with a single pass using Transformers. Extending CodeNeRF to multiple real-world scenes, Feed-forward model, Transformers.

Disentangled NeRF, Conditional NeRF, Generalizing NeRF.