a-ml
/

FaceDepth

@@ -16,7 +16,7 @@ language:
 # FaceDepth
-Face-specialized monocular depth estimation. One photo in, sharp facial relief out, with no depth sensor.
 General depth models train on streets, rooms, and furniture, so they flatten a face into a smooth blob. A face holds its information in millimeters of relief, the bridge of the nose against the cheek, the small step from lid to eyeball, and that signal sits far below what a scene-trained model represents. Face relighting, avatar capture, and AR effects need the part those models throw away.

 # FaceDepth
+Face-specialized monocular depth estimation. Trained on a dataset of labelled faces, for use on Apple Coreml, Great for selfie videos, Portrait videos, clothing and a wide variety of human faces
 General depth models train on streets, rooms, and furniture, so they flatten a face into a smooth blob. A face holds its information in millimeters of relief, the bridge of the nose against the cheek, the small step from lid to eyeball, and that signal sits far below what a scene-trained model represents. Face relighting, avatar capture, and AR effects need the part those models throw away.