A Recipe for Scaling up Text-to-Video Generation with Text-free Videos

Xiang Wang, Shiwei Zhang, Hangjie Yuan, Zhiwu Qing, Biao Gong, Yingya Zhang, Yujun Shen, Changxin Gao, Nong Sang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 6572-6582

Diffusion-based text-to-video generation has witnessed impressive progress in the past year yet still falls behind text-to-image generation. One of the key reasons is the limited scale of publicly available data (e.g. 10M video-text pairs in WebVid10M vs. 5B image-text pairs in LAION) considering the high cost of video captioning. Instead it could be far easier to collect unlabeled clips from video platforms like YouTube. Motivated by this we come up with a novel text-to-video generation framework termed TF-T2V which can directly learn with text-free videos. The rationale behind is to separate the process of text decoding from that of temporal modeling. To this end we employ a content branch and a motion branch which are jointly optimized with weights shared. Following such a pipeline we study the effect of doubling the scale of training set (i.e. video-only WebVid10M) with some randomly collected text-free videos and are encouraged to observe the performance improvement (FID from 9.67 to 8.19 and FVD from 484 to 441) demonstrating the scalability of our approach. We also find that our model could enjoy sustainable performance gain (FID from 8.19 to 7.64 and FVD from 441 to 366) after reintroducing some text labels for training. Finally we validate the effectiveness and generalizability of our ideology on both native text-to-video generation and compositional video synthesis paradigms. Code and models will be publicly available at here.