RAPTOR: Real-Time High-Resolution UAV Video Prediction with Efficient Video Attention
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (4) · 3183-3190
DOI: 10.1609/aaai.v40i4.37312 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhan Chen und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
Video prediction is plagued by a fundamental trilemma: achieving high-resolution and perceptual quality typically comes at the cost of real-time speed, hindering its use in latency-critical applications. This challenge is most acute for autonomous UAVs in dense urban environments, where foreseeing events from high-resolution imagery is non-negotiable for safety. Existing methods, reliant on iterative generation (diffusion, autoregressive models) or quadratic-complexity attention, fail to meet these stringent demands on edge hardware. To break this long-standing trade-off, we introduce RAPTOR, a video prediction architecture that achieves real-time, high-resolution performance. RAPTOR’s single-pass design avoids the error accumulation and latency of iterative approaches. Its core innovation is Efficient Video Attention (EVA), a novel translator module that factorizes spatiotemporal modeling. Instead of processing flattened spacetime tokens with O((ST)^2) or O(ST) complexity, EVA alternates operations along the spatial (S) and temporal (T) axes. This factorization reduces the time complexity to O(S + T) and memory complexity to O(max(S, T)), enabling global context modeling at 512^2 resolution and beyond, operating directly on dense feature maps with a patch-free design. Complementing this architecture is a 3-stage training curriculum that progressively refines predictions from coarse structure to sharp, temporally coherent details. Experiments show RAPTOR is the first predictor to exceed 30 FPS on a Jetson AGX Orin for 512^2 video, setting a new state-of-the-art on UAVid, KTH, and a custom high-resolution dataset in PSNR, SSIM, and LPIPS. Critically, RAPTOR boosts the mission success rate in a real-world UAV navigation task by 18%, paving the way for safer and more anticipatory embodied agents.
Zitieren
APA
Chen, Z., Guo, Z., Zhu, E., Zhang, P., Liu, X., Wang, L., & Zhang, Y. (2026). RAPTOR: Real-Time High-Resolution UAV Video Prediction with Efficient Video Attention. Proceedings of the AAAI Conference on Artificial Intelligence, 40(4), 3183-3190. https://doi.org/10.1609/aaai.v40i4.37312
Vancouver
Chen Z, Guo Z, Zhu E, Zhang P, Liu X, Wang L, et al. RAPTOR: Real-Time High-Resolution UAV Video Prediction with Efficient Video Attention. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(4):3183-3190. doi:10.1609/aaai.v40i4.37312
BibTeX
@article{Chen2026,
author = {Chen, Zhan and Guo, Zile and Zhu, Enze and Zhang, Peirong and Liu, Xiaoxuan and Wang, Lei and Zhang, Yidan},
title = {RAPTOR: Real-Time High-Resolution UAV Video Prediction with Efficient Video Attention},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {4},
pages = {3183--3190},
doi = {10.1609/aaai.v40i4.37312}
}
EUVIMED