118 citations · 120 across the 4 of their papers we have counts for
4 papers
Restereo: Diffusion stereo video generation and restoration
Xingchang Huang, Ashish Kumar Singh, Florian Dubost +6
Stereo video generation has been gaining increasing attention with recent advancements in video diffusion models. However, most existing methods focus on generating 3D stereoscopic…
Blue noise for diffusion models
Xingchang Huang, Corentin Salaün, Cristina Vasconcelos +3
Most of the existing diffusion models use Gaussian noise for training and sampling across all time steps, which may not optimally account for the frequency contents reconstructed b…
Scaling Vision Transformers to 22 Billion Parameters
Mostafa Dehghani, Josip Djolonga, Basil Mustafa +39
The scaling of Transformers has driven breakthrough capabilities for language models. At present, the largest large language models (LLMs) contain upwards of 100B parameters. Visio…
Minimizing cyber sickness in head mounted display systems: design guidelines and applications
Thiago M. Porcino, Esteban W. Clua, Cristina N. Vasconcelos +2
We are experiencing an upcoming trend of using head mounted display systems in games and serious games, which is likely to become an established practice in the near future. While…