AI Paper Atlas

Research map / Video / Video segmentation and tracking

RAPTOR: Real-Time High-Resolution UAV Video Prediction with Efficient Video Attention

Zhan Chen, Zile Guo, Enze Zhu, Peirong Zhang, Xiaoxuan Liu, Lei Wang, Yidan Zhang

AAAI 2026 · Video › Video segmentation and tracking · approach: Real-world video super-resolution · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add SpaceMix to a TimeMix-only translator (full EVA) (ablation)RAPTOR EVA translator · UAVid 512x512PSNR: 21.2 -> 28.4Improved
add TimeMix to a SpaceMix-only translator (full EVA) (ablation)RAPTOR EVA translator · UAVid 512x512PSNR: 27.1 -> 28.4Improved
replace EVA factorized translator with a ViT translator (ablation)RAPTOR · UAVid 512x512memory: Out Of MemoryHurt
add stage 2 edge (GDL) and temporal smoothness losses to L1 training (ablation)RAPTOR curriculum · UAVid 512x512SSIM: 0.603 -> 0.798Improved
add stage 3 VGG perceptual loss (ablation)RAPTOR curriculum · UAVid 512x512LPIPS: 0.102 -> 0.095Improved
add stage 3 VGG perceptual loss (ablation)RAPTOR curriculum · UAVid 512x512PSNR: 28.65 -> 28.40Hurt
use native 1024x1024 prediction instead of 512x512 for RAPTOR (ablation)GPT-4o navigation planner · real-world UAV navigationsuccess rate gain: +7% -> +18%Improved
use RAPTOR instead of SimVP/TAU at 512x512 for navigationGPT-4o navigation planner · real-world UAV navigationsuccess rate gain: +1% / +4% -> +7%Improved
RAPTOR vs SimVP on low-resolution KTHvideo predictor · KTH 10->30PSNR: 33.7 -> 32.0 PSNR; 0.905 -> 0.912 SSIMMixed
scale input resolution from 512 to 1024 for RAPTORRAPTOR · UAVidPSNR: 28.4 -> 19.3Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy