Gemino: Practical and Robust Neural Compression for Video Conferencing

no code implementations • 21 Sep 2022 • Vibhaalakshmi Sivaraman, Pantea Karimi, Vedantha Venkatapathy, Mehrdad Khani, Sadjad Fouladi, Mohammad Alizadeh, Frédo Durand, Vivienne Sze

We design Gemino, a new neural compression system for video conferencing based on a novel high-frequency-conditional super-resolution pipeline.

Super-Resolution

Efficient Video Compression via Content-Adaptive Super-Resolution

1 code implementation • ICCV 2021 • Mehrdad Khani, Vibhaalakshmi Sivaraman, Mohammad Alizadeh

SRVC decodes the video by passing the decompressed low-resolution video frames through the (time-varying) super-resolution model to reconstruct high-resolution video frames.

Super-Resolution Video Compression

Real-Time Video Inference on Edge Devices via Adaptive Model Streaming

1 code implementation • ICCV 2021 • Mehrdad Khani, Pouya Hamadanian, Arash Nasr-Esfahany, Mohammad Alizadeh

Real-time video inference on edge devices like mobile phones and drones is challenging due to the high computation cost of Deep Neural Networks.

Knowledge Distillation Semantic Segmentation +2

Adaptive Neural Signal Detection for Massive MIMO

1 code implementation • 11 Jun 2019 • Mehrdad Khani, Mohammad Alizadeh, Jakob Hoydis, Phil Fleming

We propose MMNet, a deep learning MIMO detection scheme that significantly outperforms existing approaches on realistic channels with the same or lower computational complexity.