How can we estimate camera pose and intrinsics from images when metadata are missing or unreliable? We develop calibration and pose-estimation methods that exploit structure, natural cues, and cross-view consistency. Recent directions include structure-aware direct pose estimation, extending absolute pose regression to multiple scenes, and calibration from clouds, rainbows, and horizon geometry. Calibration underpins localization, stereo depth, and distributed camera networks—linking geometric vision to long-running outdoor imaging systems.
Spotlight publications tagged for this research area.