Jaemin Cho
I am a master’s student at Stony Brook University, advised by François Rameau and co-advised by Byungkon Kang. My research centers on Spatial AI, focusing on the intersection of 3D computer vision, visual foundation models, and robot perception.
My current interests lie in scene coordinate regression for visual re-localization, with an emphasis on privacy-preserving scene encoding and omnidirectional perception.
Seeing Through the Weights: Privacy Leakage in Scene Coordinate Regression ECCV 2026
TL;DR: Recovered 3D scene and 2D images from Scene Coordinate Regression models for Visual Localization with domain agnostic images, challenging the SCR models are privacy-preserving.
Indoor 7-scenes demo