SLAMP: stochastic latent appearance and motion prediction
| Autor: | Akan, Adil Kaan, Erdem, Erkut, Erdem, Aykut, Güney, Fatma |
|---|---|
| Přispěvatelé: | Erdem, İbrahim Aykut (ORCID 0000-0002-6280-8422 & YÖK ID 20331), Güney, Fatma (ORCID 0000-0002-0358-983X & YÖK ID 187939), Akan, Adil Kaan, Erdem, Erkut, Koç Üniversitesi İş Bankası Yapay Zeka Uygulama ve Araştırma Merkezi (KUIS AI)/ Koç University İş Bank Artificial Intelligence Center (KUIS AI), College of Engineering, Graduate School of Sciences and Engineering, Department of Computer Engineering |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: | |
| Zdroj: | Proceedings of the IEEE International Conference on Computer Vision |
| Popis: | Motion is an important cue for video prediction and often utilized by separating video content into static and dynamic components. Most of the previous work utilizing motion is deterministic but there are stochastic methods that can model the inherent uncertainty of the future. Existing stochastic models either do not reason about motion explicitly or make limiting assumptions about the static part. In this paper, we reason about appearance and motion in the video stochastically by predicting the future based on the motion history. Explicit reasoning about motion without history already reaches the performance of current stochastic models. The motion history further improves the results by allowing to predict consistent dynamics several frames into the future. Our model performs comparably to the state-of-the-art models on the generic video prediction datasets, however, significantly outperforms them on two challenging real-world autonomous driving datasets with complex motion and dynamic background. Comment: ICCV 2021 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|