3D Portrait (Photo to 3D Demo)
A TensorFlow.js demo that estimates depth from a single portrait photo and turns it into a moving 3D photo. It shows the original, the segmented subject, the depth map and the 3D result side by side, so you can see each stage. The result can be downloaded as a GIF or WebM.
How to try it
Try the numbered example photos 1–10 first, then drag your own portrait into the upload area or click to select one. Once uploaded you can crop it and processing starts automatically; the Controls panel on the right adjusts wireframe, minDepth and maxDepth, background and camera speed, and the result downloads as GIF or WebM. The first run takes over three seconds to initialise the model and later ones are faster; the page is English only.