Adobe’s new AI experiment syncs your dance moves perfectly to the beat
TikTok has made on-beat dances and movements mainstream. But what if you went offbeat or the video you recorded had some lag to your perfect dance moves. Adobe can fix that for you. The ...
NVIDIA Broadcast: Die ultimative KI-gestützte App für Sprach- und Videokommunikation
Verwandle deine Livestreams, Voice Chats und Videoanrufe mit leistungsstarken KI-Effekten wie Rauschunterdrückung und virtuellen Hintergründen.
3D facial capture using a custom-built photogrammetry setup for Orthodontics - 3Dflow
3D facial capture using a custom-built photogrammetry setup for Orthodontics Digital Orthodontics, Facial Capturing, Medical Engineering The data for this case study has been kindly provided by Hans Wellens – a Belgian orthodontist who obtained a Ph.D. at … Read More
Few-Shot Video-to-Video Synthesis (NeurIPS 2019)
Few-shot photorealistic video-to-video translation. It can be used for generating human motions from poses, synthesizing people talking from edge maps, or tu...
Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data - CVPR 2020
AbstractWe present a novel method for monocular hand shape and pose estimation at unprecedented runtime performance of 100fps and at state-of-the-art accurac...
DeepCap: Monocular Human Performance Capture Using Weak Supervision (CVPR 2020) - Oral
Human performance capture is a highly important computer vision problem with many applications in movie production and virtual/augmented reality. Many previo...
3DF Zephyr Development Status Progress – Dragonfruit – Part 3 - 3Dflow
With today’s update, we continue our tour of what’s coming up for 3DF Zephyr 5.0 – codename Dragonfruit. This quick update is mostly dedicated to user interface and tool availability improvements – we will discuss more about the underlying technology … Read More