Papers › Video Prediction Transformers without Recurrence or Convolution

Video Prediction Transformers without Recurrence or Convolution

7 Oct 2024arXiv:2410.04733archive 2025-07-28

Yujin Tang, Lu Qi, Fei Xie, Xiangtai Li, Chao Ma, Ming-Hsuan Yang

Video prediction has witnessed the emergence of RNN-based models led by ConvLSTM, and CNN-based models led by SimVP. Following the significant success of ViT, recent works have integrated ViT into both RNN and CNN frameworks, achieving improved performance. While we appreciate these prior approaches, we raise a fundamental question: Is there a simpler yet more effective solution that can eliminate the high computational cost of RNNs while addressing the limited receptive fields and poor generalization of CNNs? How far can it go with a simple pure transformer model for video prediction? In this paper, we propose PredFormer, a framework entirely based on Gated Transformers. We provide a comprehensive analysis of 3D Attention in the context of video prediction. Extensive experiments demonstrate that PredFormer delivers state-of-the-art performance across four standard benchmarks. The significant improvements in both accuracy and efficiency highlight the potential of PredFormer as a strong baseline for real-world video prediction applications. The source code and trained models will be released at https://github.com/yyyujintang/PredFormer.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

yyyujintang/predformer officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Decoder Prediction Video Prediction

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Video Prediction	Moving MNIST	PredFormer	MAE	41.96	#1 of 31	Archive leaderboard	report
Video Prediction	Moving MNIST	PredFormer	MSE	11.62	#1 of 31	Archive leaderboard	report
Video Prediction	Moving MNIST	PredFormer	PSNR	39.89	#1 of 31	Archive leaderboard	report
Video Prediction	Moving MNIST	PredFormer	SSIM	0.9742	#1 of 31	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BPE ConvLSTM Convolution Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Sigmoid Activation Softmax Tanh Activation Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections