2001.04.02
<aside> 🌱 I have a background in web backend development. Recently, I’ve developed a strong interest and passion for AI technology development and research, particularly in the areas of vision(3D) and human-centered AI. I’ve also actively participated in several educational programs because I believe education is the most powerful way to foster positive change in society.
</aside>
(M.S./PhD integrated) Seoul National University (SNU)
(B.S.) Gwangju Institute of Science and Technology (GIST)
Research interest
Contact
Github: https://github.com/SojeongKim-42
Now in an intergated course(M.S.) at SNU AIoT Lab. Developed fundamentals of 3D vision, assisting in some research on building a 3D dataset. I am particularly interested in leveraging egocentric perspectives to enhance 3D vision systems. Currently exploring multimodal 3D scene understanding, with a focus on integrating diverse sensor inputs to perceive and interpret physical environments.
Interned at GIST Computer Graphics Lab and conducted bachelor’s thesis research ****at the intersection of neural rendering and image processing. Applied a cross-bilateral filter to quickly rendered low-spp images guided by NeRF outputs, achieving significant RSE reductions. This approach effectively improved both rendering time and image quality, by just inferencing from a pretrained NeRF model.
Created data classification rules using regular expressions and SQL queries. Identified inefficiencies in the internal management site and took initiative to fix bugs and add new features using React and Scala. Proposed the adoption of ML to detect misclassifications and led the cross-team collaboration to integrate it.
Introduced EgoXtreme: A Dataset for Robust Object Pose Estimation in Egocentric Views under Extreme Conditions, a large-scale egocentric 6D pose estimation dataset designed to bridge the gap between controlled laboratory settings and chaotic real-world applications. The benchmark features three challenging scenarios—maintenance, sports, and emergency—characterized by severe visual degradations such as extreme lighting, heavy motion blur, and smoke. I contributed to the project as an early member, participating in the end-to-end pipeline.