Typing remains a primary mode of interaction in extended reality (XR), yet most XR systems still depend on physical keyboards or specialized sensing hardware. We present a visiononly keystroke tracking pipeline for surface typing that combines visible-key detection, recovery of hand-occluded keys, and finger keypress event detection on monocular video. The system first detects the keyboard and visible keys with a YOLO-based detector trained on oriented key boxes and synthetic hand-occlusion augmentation. Occluded or missed keys are then recovered with lightweight per-key regressors driven by an efficient 3–2 recovery-key selection strategy. For keypress detection, we use monocular 3D hand reconstruction with HaMeR and an autoregressive transformer that processes temporal image sequences, recovered hand meshes, finger keypoint masks, and camera poses to estimate press-down probabilities for each finger. On the Keyboard Key Detection dataset, our visible-key detector achieves 97% mAP@75 with mean IoU around 0.9, while occluded-key recovery sustains 30 fps. On typing videos from the MSU Typing Behavior Database, the keypress module reaches up to 90% event detection accuracy with 28 ms latency. Together, these components form a practical end-to-end vision system for hardware-free keystroke tracking on printed, projected, or rendered keyboard layouts.