How to convert 2D video to spatial video on Apple Vision Pro

Choose a suitable source

Select an ordinary video with visible foreground and background separation. A steady clip with recognisable objects gives a depth model more information than fast motion, heavy blur or a nearly flat scene.

Understand the local conversion

Twineye analyses frames with a depth model bundled in the app, synthesises a second viewpoint and encodes the result as MV-HEVC. The source is not uploaded and processing does not require a cloud service.

• Import the selected video
• Let the device estimate depth and encode
• Save the result to the location you control

Review the result on Vision Pro

Synthetic spatial video is different from footage captured with two cameras. Check depth comfort, edges and motion in the final viewing environment, and keep the original file so you can try another source if needed.