12 citations · 22 across the 10 of their papers we have counts for
3 papers · 1 filter
Clockwork Diffusion: Efficient Generation With Model-Step Distillation
Amirhossein Habibian, Amir Ghodrati, Noor Fathima +4
This work aims to improve the efficiency of text-to-image diffusion models. While diffusion models use computationally expensive UNet-based denoising operations in every generation…
MobileNVC: Real-time 1080p Neural Video Compression on a Mobile Device
Ties van Rozendaal, Tushar Singhal, Hoang Le +10
Neural video codecs have recently become competitive with standard codecs such as HEVC in the low-delay setting. However, most neural codecs are large floating-point networks that…
A Residual Diffusion Model for High Perceptual Quality Codec Augmentation
Noor Fathima Ghouse, Jens Petersen, Auke Wiggers +2
Diffusion probabilistic models have recently achieved remarkable success in generating high quality image and video data. In this work, we build on this class of generative models…