Avatar Creation SDK, Instant 3D Avatars, Pinscreen Inc., Los Angeles, California, USA

[Airicist]

Developer - Pinscreen Inc. (https://pr.ai/showthread.php?t=21065)

pinscreen.com/avatarsdk (https://pinscreen.com/avatarsdk)

pinscreen.com/mobileapp (https://pinscreen.com/mobileapp)

[Airicist]

https://youtu.be/UPcR7S8ue1A

AI-Based Animoji without the iPhone X | Two Minute Papers #236

Published on Mar 15, 2018


The paper "Avatar Digitization From a Single Image For Real-Time Rendering" is available here:

hao-li.com/Hao_Li/Hao_Li_-_publications.html (http://www.hao-li.com/Hao_Li/Hao_Li_-_publications.html)

"Avatar Digitization From a Single Image For Real-Time Rendering (http://www.hao-li.com/publications/papers/siggraphAsia2017ADFSIFRTR.pdf)"

[Airicist]

https://youtu.be/_JMx5VN1eeM

paGAN: Real-time Avatars Using Dynamic Textures (SIGGRAPH Asia 2018)

Published on Nov 24, 2018


SIGGRAPH Asia 2018 Paper Video: With the rising interest in personalized VR and gaming experiences comes the need to create high quality 3D avatars that are both low-cost and variegated. Due to this, building dynamic avatars from a single unconstrained input image is becoming a popular application. While previous techniques that attempt this require multiple input images or rely on transferring dynamic facial appearance from a source actor, we are able to do so using only one 2D input image without any form of transfer from a source image. We achieve this using a new conditional Generative Adversarial Network design that allows fine-scale manipulation of any facial input image into a new expression while preserving its identity. Our photoreal avatar GAN (paGAN) can also synthesize the unseen mouth interior and control the eye-gaze direction of the output, as well as produce the final image from a novel viewpoint. The method is even capable of generating fully-controllable temporally stable video sequences, despite not using temporal information during training. After training, we can use our network to produce dynamic image-based avatars that are controllable on mobile devices in real time. To do this, we compute a fixed set of output images that correspond to key blendshapes, from which we extract textures in UV space. Using a subject’s expression blendshapes at run-time, we can linearly blend these key textures together to achieve the desired appearance. Furthermore, we can use the mouth interior and eye textures produced by our network to synthesize on-the-fly avatar animations for those regions. Our work produces state-of-the-art quality image and video synthesis, and is the first to our knowledge that is able to generate a dynamically textured avatar with a mouth interior, all from a single image.

[Airicist]

https://youtu.be/wbgbOSwDcQ8

Pinscreen App: Instant 3D Avatars (2019)

Published on Mar 29, 2019


This is a live demo of the latest Pinscreen iOS App (March 2019) for instant 3D avatar creation. Simply upload a selfie or any picture, and within seconds, Pinscreen generates your personal 3D avatar. You can bring your avatar to life through your facial performance, and change its clothing and hairstyle. Immerse yourself in new virtual places and share your personalized avatar emotes.

[Airicist]

Article "A Deepfake Putin and the Future of AI Take Center Stage at Emtech (https://www.pcmag.com/article/370887/a-deepfake-putin-and-the-future-of-ai-take-center-stage-at-e)"
Deepfake technology got a lot of attention, but I was more interested in the future directions for AI research.

by Michael J. Miller
September 20, 2019

[Airicist]

"Los Angeles-Based Artificial Intelligence Company Pinscreen Announces the Hiring of Leading Digital Artist Anda Deng (https://www.prnewswire.com/news-releases/los-angeles-based-artificial-intelligence-company-pinscreen-announces-the-hiring-of-leading-digital-artist-anda-deng-301355351.html)"

August 16, 2021