CVPR 2023 Text Guided Video Editing Competition
Jay Zhangjie Wu, Xiuyu Li, Difei Gao, Zhen Dong, Jinbin Bai, Aishani, Singh, Xiaoyu Xiang, Youzeng Li, Zuwei Huang, Yuanxi Sun, Rui He, Feng Hu,, Junhua Hu, Hai Huang, Hanyu Zhu, Xu Cheng, Jie Tang, Mike Zheng Shou, Kurt, Keutzer, Forrest Iandola
TL;DR
This paper introduces a new dataset and competition for text-guided video editing, aiming to standardize evaluation and advance AI capabilities in video editing tasks.
Contribution
It presents the first benchmark dataset for text-guided video editing and organizes a CVPR competition to evaluate and compare different models.
Findings
The competition dataset is publicly available.
The paper reviews the top-performing methods.
It highlights current challenges in text-guided video editing.
Abstract
Humans watch more than a billion hours of video per day. Most of this video was edited manually, which is a tedious process. However, AI-enabled video-generation and video-editing is on the rise. Building on text-to-image models like Stable Diffusion and Imagen, generative AI has improved dramatically on video tasks. But it's hard to evaluate progress in these video tasks because there is no standard benchmark. So, we propose a new dataset for text-guided video editing (TGVE), and we run a competition at CVPR to evaluate models on our TGVE dataset. In this paper we present a retrospective on the competition and describe the winning method. The competition dataset is available at https://sites.google.com/view/loveucvpr23/track4.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Multimodal Machine Learning Applications · Human Motion and Animation
MethodsDiffusion