

Koki Nagano
9.2K posts

@luminohope
Principal Research Scientist @NVIDIA Research. Views are my own










Join us at the workshop on Photo-realistic 3D Head Avatars at #CVPR2025, featuring invited talks by leading academic researchers and industry professionals at the forefront of avatar technology. Wednesday 11th, starting from 1:20pm workshop website: kaldir.vc.in.tum.de/nersemble_benc…






Join us at the workshop on Photo-realistic 3D Head Avatars at #CVPR2025, featuring invited talks by leading academic researchers and industry professionals at the forefront of avatar technology. Wednesday 11th, starting from 1:20pm workshop website: kaldir.vc.in.tum.de/nersemble_benc…



A purely synthetic face prior can generalize to casual in-the-wild captures and stylized faces 🤯 I'm happy to share our @SIGGRAPHAsia paper “Cafca: High-quality Novel View Synthesis of Expressive Faces from Casual Few-shot Captures.” syntec-research.github.io/Cafca/



@1x_tech @NVIDIARobotics We've found Cosmos to a really good tokenizer, much better than Magvit2 fine-tuned on our data. Here are some example tokens from our released dataset that we decoded back to video:


👾 Discover the Future of #DigitalHumans with #NVIDIA! Join Koki Nagano (@luminohope) as he unpacks @nvidia’s latest in realistic 3D human models. 📅 3 Dec | 2.15pm 📍 TIF, Hall C Register for #SIGGRAPHAsia2024 in Tokyo now! 🎟️👉 bit.ly/sa24reg #SAfeaturedsessions