SyncVP: Joint Diffusion for Synchronous Multi-Modal Video Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916660957413376 |
|---|---|
| author | Pallotta, Enrico Azar, Sina Mokhtarzadeh Li, Shuai Zatsarynna, Olga Gall, Juergen |
| author_facet | Pallotta, Enrico Azar, Sina Mokhtarzadeh Li, Shuai Zatsarynna, Olga Gall, Juergen |
| contents | Predicting future video frames is essential for decision-making systems, yet RGB frames alone often lack the information needed to fully capture the underlying complexities of the real world. To address this limitation, we propose a multi-modal framework for Synchronous Video Prediction (SyncVP) that incorporates complementary data modalities, enhancing the richness and accuracy of future predictions. SyncVP builds on pre-trained modality-specific diffusion models and introduces an efficient spatio-temporal cross-attention module to enable effective information sharing across modalities. We evaluate SyncVP on standard benchmark datasets, such as Cityscapes and BAIR, using depth as an additional modality. We furthermore demonstrate its generalization to other modalities on SYNTHIA with semantic information and ERA5-Land with climate data. Notably, SyncVP achieves state-of-the-art performance, even in scenarios where only one modality is present, demonstrating its robustness and potential for a wide range of applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_18933 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SyncVP: Joint Diffusion for Synchronous Multi-Modal Video Prediction Pallotta, Enrico Azar, Sina Mokhtarzadeh Li, Shuai Zatsarynna, Olga Gall, Juergen Computer Vision and Pattern Recognition Predicting future video frames is essential for decision-making systems, yet RGB frames alone often lack the information needed to fully capture the underlying complexities of the real world. To address this limitation, we propose a multi-modal framework for Synchronous Video Prediction (SyncVP) that incorporates complementary data modalities, enhancing the richness and accuracy of future predictions. SyncVP builds on pre-trained modality-specific diffusion models and introduces an efficient spatio-temporal cross-attention module to enable effective information sharing across modalities. We evaluate SyncVP on standard benchmark datasets, such as Cityscapes and BAIR, using depth as an additional modality. We furthermore demonstrate its generalization to other modalities on SYNTHIA with semantic information and ERA5-Land with climate data. Notably, SyncVP achieves state-of-the-art performance, even in scenarios where only one modality is present, demonstrating its robustness and potential for a wide range of applications. |
| title | SyncVP: Joint Diffusion for Synchronous Multi-Modal Video Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.18933 |