• Akram Khan
• Ramkumar Maurya
• Swaraj Patil
• Fahad Shaikh
• Danish Koradia

This paper proposes an efficient, lightweight framework for real-time dynamic avatar animation. Our framework can generate all facial expressions, gestures, and torso movements accurately. The key to our technique lies solely in utilizing the camera sensor of your laptop or an webcam. The magic happens through the combination of various technologies, including MediaPipe, Three.js, and Kalidokit. Specifically, MediaPipe within our framework calculates the 3D posture and facial landmarks of the captured subject. A mapping function then transforms this data to control the avatar's rigid skeleton. This approach eliminates the need for expensive motion capture sensors and the technical expertise required for traditional animation. As a result, our framework offers a simple and user-friendly solution for animating avatars in various applications. By providing open-access to the framework, our aim is to facilitate collaboration and innovation in the field of motion capture technology.

"REAL TIME 3D AVATAR ANIMATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.p90-p95, April-2024, Available :http://www.jetir.org/papers/JETIR2404G11.pdf

"REAL TIME 3D AVATAR ANIMATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppp90-p95, April-2024, Available at : http://www.jetir.org/papers/JETIR2404G11.pdf