Ph.D. graduate in Computer Science from University of Washington
Hello! I am an Applied Scientist at Flawless AI working on cutting-edge generative AI technology for filmmaking. Previously I was a Research Scientist in the XR Tech team at Meta Reality Labs working on AI algorithms for different immersive AR/VR/MR applications. I completed my Ph.D. in Computer Science and Engineering from University of Washington under the guidance of Prof. Linda Shapiro (GRAIL) and Dr. Alex Colburn (Apple). Previously, I completed my Masters in Electrical Engineering from Indian Institute of Technology Bombay under the guidance of Prof. Subhasis Chaudhuri and received my Bachelors in Electronics and Telecommunication Engineering from Jadavpur University under the guidance of Prof. Iti Saha Misra.
My research interests are in the fields of Computer Vision (generative AI), Computer Graphics (3D humans/perception) and Deep Learning, focusing on high-resolution video synthesis and photorealistic 3D human modeling. My PhD thesis was on human facial expression modeling using deep learning frameworks and real-time facial motion retargeting from 2D images to 3D characters. During my PhD, I also got the opportunity to work on a variety of exciting projects as a research intern at Microsoft Research, Facebook Reality Labs Research and Intel Labs.
Flawless AI (Santa Monica, CA)
3D face neural rendering for visual dubbing and multilingual audio-driven photorealistic 3D facial animation
XR Tech team, Meta Reality Labs (Redmond, WA)
[Gen AI] Image-to-video synthesis using 3D-VQGAN and masked generative transformer
[Gen AI] Depth-guided Text-to-video synthesis
[3D Humans] Text/speech driven 3D human animation prediction for embodied AI
[3D Faces] Multimodal (audio-visual) detailed 4D face geometry reconstruction
[3D Faces] Speech-driven real-time 3D facial animation with emotions and non-speech vocalizations
[3D Faces] Video-based dynamic 3D face texture completion to handle occlusions
[3D Faces] StyleGAN-based improved face texture recovery
Virtual Humans team, Facebook Reality Labs Research (Sausalito, CA)
Photorealistic editable texture map synthesis for 3D humans for virtual try-on applications
AI Perception and Mixed Reality Platform team, Microsoft Cloud & AI (Redmond, WA)
Personalized face modeling for high-fidelity 3D reconstruction and improved 3D tracking and retargeting from 2D images
Visual Intelligence group, Microsoft Research (Redmond, WA)
Real-time multi-task deep learning framework to transfer performance of human face(s) from 2D images to 3D animated characters
Integrated in Puppets feature of Swiftkey for Android phone users! [Media report]
Computational Imaging Lab, Intel Labs (Santa Clara, CA)
Deep optical flow prediction and image super-resolution for efficient frame interpolation/view synthesis from high-definition multi-camera array images
US patent granted!
Department of Information Engineering and Computer Science, University of Trento (Trento, Italy)
Novel unsupervised and semi-supervised approaches to content-based retrieval of remote sensing images using an inexact graph matching strategy.
University of Washington and IIT Bombay
Courses taught: Computer Vision, Artificial Intelligence, Algorithms, Compilers, Digital Signal Processing, Digital Communications
Deepali Aneja, Bindita Chaudhuri, Alex Colburn, Gary Faigin, Linda Shapiro and Barbara Mones
IEEE Winter Conference on Applications of Computer Vision (WACV), 2018People's Choice Award! [Allen School News] [Geekwire article]
