NVIDIA Neural Talking-Head Synthesis Video Conferencing Deepfakes
While Lucasfilm hired the VFX artist who created Star Wars deepfake videos on YouTube, NVIDIA’s neural talking-head synthesis took a different approach. This model takes deepfakes to the next level as it’s capable of synthesizing a talking-head video using a source image containing the target person’s appearance and a driving video that dictates the motion in the output.



This motion is then encoded based on a novel key point representation, where the identity-specific and motion-related information is decomposed without supervision. Extensive experimental validation showed that their model outperforms competing methods on benchmark datasets. Plus, their compact key point representation enables a video conferencing system that achieves the same visual quality as the commercial H.264 standard while only using one-tenth of the bandwidth.

Mini Pc Windows 11 Pro Computers with Intel 11th Gen 4 Cores N5095 Up to 2.9Ghz 8GBD DDR4 256GB SSD,Dual HDMI 4K 60hz/Gigabit Ethernet/Dual WiFi/BT/Support 2.5' HDD/SSD
38 Reviews
Mini Pc Windows 11 Pro Computers with Intel 11th Gen 4 Cores N5095 Up to 2.9Ghz 8GBD DDR4 256GB SSD,Dual HDMI 4K 60hz/Gigabit Ethernet/Dual WiFi/BT/Support 2.5" HDD/SSD
  • 【High performance 】Intel 11th Generation N5095 (4 Cores/4 Threads 4M Cache, up to 2.9Ghz ). 8GB DDR4/256GB M.2 SSD,Intel HD Graphics ,2.4G/5G WIFI...
  • 【Rich interface】Supports up to 2 monitors connected at the same time (HDMI+HDMI), 4 USB 3.0 ports, 1*3.5mm audio port, 36w power supply, energy...
  • 【Windows 11 PRO】Built-in windows 11 pro system, support ubuntu/linux

Besides, we show our keypoint representation allows the user to rotate the head during synthesis, which is useful for simulating a face-to-face video conferencing experience,” said the researchers.

Write A Comment