Jun 6, 2024 · We propose VideoTetris, a novel framework that enables compositional T2V generation. Specifically, we propose spatio-temporal compositional diffusion.

VideoTetris is a novel framework that enables compositional T2V generation. Specifically, we propose spatio-temporal compositional diffusion to precisely follow ...

We propose VideoTetris, a novel framework that enables compositional T2V generation. Specifically, we propose spatio-temporal compositional diffusion.

Jun 6, 2024 · We propose VideoTetris, a novel framework that enables compositional T2V generation. Specifically, we propose spatio-temporal compositional diffusion.

The paper presents "VideoTetris," a new framework designed to improve text-to-video generation in complex scenarios with dynamic changes and multiple objects.

Extensive experiments demonstrate that our VideoTetris achieves impressive qualitative and quantitative results in compositional T2V generation. 1 Introduction.

Diffusion models have demonstrated great success in text-to-video (T2V) generation. However, existing methods may face challenges when handling complex ...

The proposed VideoTetris is a novel framework that enables compositional T2V generation, equipped with a new reference frame attention mechanism to improve ...

Jun 7, 2024 · [2406.04277] VideoTetris: Towards Compositional Text-to-Video Generation · Comments Section · Community Info Section · More posts you may like.

Jul 24, 2024 · This paper introduces the 1st compositional Text-to-video generation benchmark, T2V-CompBench. It evaluates diverse aspects of compositionality.