Journal
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
Volume -, Issue -, Pages 3160-3170Publisher
IEEE COMPUTER SOC
DOI: 10.1109/CVPR52688.2022.00317
Keywords
-
Funding
- Science and Technology Innovation 2030 -Major Project [2021ZD0150100]
- National Natural Science Foundation of China [U21A20427]
Ask authors/readers for more resources
This paper proposes SimVP, a simple and efficient video prediction model that is built upon CNN and trained by MSE loss. Despite its simplicity, SimVP achieves state-of-the-art performance on multiple benchmark datasets. Extended experiments demonstrate its strong generalization and scalability, with significantly reduced training cost.
From CNN, RNN, to ViT, we have witnessed remarkable advancements in video prediction, incorporating auxiliary inputs, elaborate neural architectures, and sophisticated training strategies. We admire these progresses but are confused about the necessity: is there a simple method that can perform comparably well? This paper proposes SimVP, a simple video prediction model that is completely built upon CNN and trained by MSE loss in an end-to-end fashion. Without introducing any additional tricks and complicated strategies, we can achieve state-of-the-art performance on five benchmark datasets. Through extended experiments, we demonstrate that SimVP has strong generalization and extensibility on real-world datasets. The significant reduction of training cost makes it easier to scale to complex scenarios. We believe SimVP can serve as a solid baseline to stimulate the further development of video prediction.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available