Papers › Efficient and Information-Preserving Future Frame Prediction and Beyond

Efficient and Information-Preserving Future Frame Prediction and Beyond

1 May 2020ICLR 2020 1archive 2025-07-28

Wei Yu, Yichao Lu, Steve Easterbrook, Sanja Fidler

Applying resolution-preserving blocks is a common practice to maximize information preservation in video prediction, yet their high memory consumption greatly limits their application scenarios. We propose CrevNet, a Conditionally Reversible Network that uses reversible architectures to build a bijective two-way autoencoder and its complementary recurrent predictor. Our model enjoys the theoretically guaranteed property of no information loss during the feature extraction, much lower memory consumption and computational efficiency. The lightweight nature of our model enables us to incorporate 3D convolutions without concern of memory bottleneck, enhancing the model's ability to capture both short-term and long-term temporal dependencies. Our proposed approach achieves state-of-the-art results on Moving MNIST, Traffic4cast and KITTI datasets. We further demonstrate the transferability of our self-supervised learning method by exploiting its learnt features for object detection on KITTI. Our competitive results indicate the potential of using CrevNet as a generative pre-training strategy to guide downstream tasks.

Paper PDF Code

Code

rrxi/CrevNet pytorch 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

Computational Efficiency Object Detection Prediction Self-Supervised Learning Video Prediction object-detection

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Video Prediction	Moving MNIST	CrevNet+ST-LSTM	MSE	22.3	#17 of 31	Archive leaderboard	report
Video Prediction	Moving MNIST	CrevNet+ST-LSTM	SSIM	0.949	#17 of 31	Archive leaderboard	report
Video Prediction	Moving MNIST	CrevNet+ConvLSTM	MSE	38.5	#22 of 31	Archive leaderboard	report
Video Prediction	Moving MNIST	CrevNet+ConvLSTM	SSIM	0.928	#22 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.

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