Animating General Image with Large Visual Motion Model

Dengsheng Chen, Xiaoming Wei, Xiaolin Wei; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 7131-7140

Abstract

We present the pioneering Large Visual Motion Model (LVMM) meticulously engineered to analyze the intrinsic dynamics encapsulated within real-world imagery. Our model fortified with a wealth of prior knowledge extracted from billions of image pairs demonstrates promising results in predicting a diverse spectrum of scene dynamics. As a result it can infuse any generic image with authentic dynamic effects enhancing its visual allure.

Related Material

[pdf] [supp]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Dengsheng and Wei, Xiaoming and Wei, Xiaolin}, title = {Animating General Image with Large Visual Motion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7131-7140} }