DeepMotion’s Animate 3D provides full-body tracking from a simple video input. In order for our service to generate 3D animations accurately, there are a subset of guidelines that should be followed in order to generate the best animation possible. Our team continually works on improving the overall tracking quality on our end, but as a user, there are some things you can do to help improve your results!
Check out this Video Capture Guidelines video for a walkthrough on what you can do to help our AI track your videos for better markerless motion capture.
VIDEO CAPTURE GUIDELINES
Subject: The person you are capturing should be a human - no cartoons or other digital characters.
Camera: Should be stationary and perpendicular to your subject.
Character Placement: The entire body from head to toe should be visible, located 2-6 meters (6-20 feet) from the camera.
Lighting: Neutral lighting with high contrast between the subject and the background is recommended.
Occlusion: The subject should not be occluded by any objects and there should be a single subject in the motion clip.
Clothing: Do not wear loose clothing or clothing that covers key joints like knees and elbows. Exposed joints are best! Clothing color should vary, not be all solid colors like all black, with patterns being highly recommended.
Size: Please review our pricing page for limits on upload length and video size per subscription plan.