FAQ
This page consists of MotionPortrait FAQs. If you cannot find the answer you’re looking for, please ask your question using this form.
General Questions
- What is MotionPortrait?
- MotionPortrait is a technology that can create a variety of facial expression animations from a single image. Please check "What is MotionPortrait?" to see more information.
- Wow! But how can I use it for?
- The possibilities are limitless. Please check "Solutions" page.
- How many pictures are needed?
- Only one picture is necessary.
- Do I have to use a special camera?
- No. You can use a regular digital camera. You can even use the camera on your mobile phone.
- This must be a video clip, right?
- No. This is a 100% computer-generated image.
- How long does it take to create the animation after taking a picture?
- It normally takes only a few seconds on a PC.
- Can I create an animation that makes a model turn to the side or turn the other way?
- It is possible to make the model turn to some degree. The image looks natural within ±20 degrees. Since we have no back image, an animation of the back of the head would look unnatural.
- Can I automatically make a model from a non-human?
- It is hard to recognize non-human models automatically, so the model must be created manually. After creating a model, the animation is created automatically.
- Was MotionPortrait originally a Sony technology?
- Yes. MotionPortrait, Inc. was created by members who had originally developed the technology at the former Sony-Kihara Research Center.
Technical Questions
- What are the minimum requirements for my PC?
- A computer with a 1-Ghz CPU can create animations in real time. MotionPortrait should still work reasonably well with computers that do not meet these specifications.
- How smoothly can it animate on a mobile phone?
- We have confirmed approximately 30 fps with a graphic accelerator and 15 fps without one.
- 3. If I take a picture from the side and use it, can I make a perfect 3D head model?
- Technically, yes. However, MotionPortrait uses only one picture because of the following reasons:
a: Taking multiple pictures is more time-consuming.
b: The animation quality worsens when multiple images are used. - Can I make lip-sync automatically?
- Yes, this is certainly possible. You can match lip movements with voice in real time using the microphone.
- I want to use it for game production.
- We can offer a middleware. Please contact Silicon Studio Corporation at the address below:
http://www.gametools.jp/products2.html#motion - 6. Does the automatic process for creating 3D models ever fail?
- Yes, but this is very rare. If this ever happens, you can easily correct the mistake.