Video editing via factorized diffusion distillation

U Singer, A Zohar, Y Kirstain, S Sheynin… - … on Computer Vision, 2024 - Springer
Abstract We introduce Emu Video Edit (EVE), a model that establishes a new state-of-the art
in video editing without relying on any supervised video editing data. To develop EVE we …

Omnissr: Zero-shot omnidirectional image super-resolution using stable diffusion model

R Li, X Sheng, W Li, J Zhang - European Conference on Computer Vision, 2024 - Springer
Omnidirectional images (ODIs) are commonly used in real-world visual tasks, and high-
resolution ODIs help improve the performance of related visual tasks. Most existing super …

DiffLLE: Diffusion-based Domain Calibration for Weak Supervised Low-light Image Enhancement

S Yang, X Zhang, Y Wang, J Yu, Y Wang… - International Journal of …, 2024 - Springer
Existing weak supervised low-light image enhancement methods lack enough effectiveness
and generalization in practical applications. We suppose this is because of the absence of …

Searching Priors Makes Text-to-Video Synthesis Better

H Cheng, L Peng, L **a, Y Hu, H Li, Q Lu, X He… - arxiv preprint arxiv …, 2024 - arxiv.org
Significant advancements in video diffusion models have brought substantial progress to the
field of text-to-video (T2V) synthesis. However, existing T2V synthesis model struggle to …

OmniFusion: Exemplar-Based Video Colorization Using OmniMotion and DifFusion Priors

X Fang, L Dai, J Tang - Proceedings of the Asian …, 2024 - openaccess.thecvf.com
Exemplar-based video colorization is a challenging task that involves the consistent
propagation of colors across frames and the reasonable inference of colors from grayscale …

Via: A spatiotemporal video adaptation framework for global and local video editing

J Gu, Y Fang, I Skorokhodov, P Wonka, X Du… - 2024 - repository.kaust.edu.sa
Video editing stands as a cornerstone of digital media, from entertainment and education to
professional communication. However, previous methods often overlook the necessity of …