Taneem Ullah Jan

I am working and contributing to the advancement in the field of 3D neural head avatars and virtual humans using computer graphics, computer vision, and deep neural networks. I serve as an AI Researcher at VOLV AI, where I direct the machine learning team in exploring innovative solutions in 3D computer vision for virtual try-on and digital human synthesis. Previously, I worked as a Research AI Engineer at BHuman AI, leading the research and development for their core generative AI products.

connect and contact

• CV — GitHub — Twitter — LinkedIn

• taneemishere[@]gmail[.]com

research and projects

• OmniFit-3D: A Unified Framework for 3D Virtual Try-On with Pose-Adaptive Realism

  A unified framework for 3D virtual try-on that transforms simple 2D images into realistic 3D representations, by efficiently integrating clothing with the human body in a pose-adaptive manner.

  [project page]




• LipSyncFace: High-Fidelity Audio-Driven and Lip-Synchronized Talking Face Generation

  A two-stage unified audio-driven talking face generation framework, which can render high-fidelity, lip-synchronized videos with improved inference speed.

  [project page]




• Beyond CNNs: Encoded Context for Image Inpainting with LSTMs and Pixel CNNs

  Current image inpainting techniques are too heavy; this paper introduces a Row-wise Flat Pixel LSTM, a small hybrid model for the efficient and high-quality restoration of small images.

  [project page] [PDF]




• lipsync2: Talking Face Generation with Most Accurate Lip Synchronization

  A robust and efficient talking face generation model with highly accurate lip synchronization and full facial expressiveness with more extended audio and high-quality video resolutions.

  [project page]




• face2face: One-Shot Talking Head Video Generation from a Static Source Image

  An unsupervised one-shot talking head video generation model using neural rendering and motion transfer techniques with non-linear transformation to animate static images.

  [project page]




• face-swapping: Swapping Faces on Target from given Sources

  Innovative face-swapping model that preserves the source identity features accurately while seamlessly adapting target attributes applicable to images and videos.

  [project page]




• HTML Code Generation from Images with Deep Neural Networks

  An accurate deep learning model converting GUI mockups into HTML code, streamlining web development for non-programmers.

  [project page] [code] [demo]