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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add SpaceMix to a TimeMix-only translator (full EVA) (ablation) | RAPTOR EVA translator · UAVid 512x512 | PSNR: 21.2 -> 28.4 | Improved |
| add TimeMix to a SpaceMix-only translator (full EVA) (ablation) | RAPTOR EVA translator · UAVid 512x512 | PSNR: 27.1 -> 28.4 | Improved |
| replace EVA factorized translator with a ViT translator (ablation) | RAPTOR · UAVid 512x512 | memory: Out Of Memory | Hurt |
| add stage 2 edge (GDL) and temporal smoothness losses to L1 training (ablation) | RAPTOR curriculum · UAVid 512x512 | SSIM: 0.603 -> 0.798 | Improved |
| add stage 3 VGG perceptual loss (ablation) | RAPTOR curriculum · UAVid 512x512 | LPIPS: 0.102 -> 0.095 | Improved |
| add stage 3 VGG perceptual loss (ablation) | RAPTOR curriculum · UAVid 512x512 | PSNR: 28.65 -> 28.40 | Hurt |
| use native 1024x1024 prediction instead of 512x512 for RAPTOR (ablation) | GPT-4o navigation planner · real-world UAV navigation | success rate gain: +7% -> +18% | Improved |
| use RAPTOR instead of SimVP/TAU at 512x512 for navigation | GPT-4o navigation planner · real-world UAV navigation | success rate gain: +1% / +4% -> +7% | Improved |
| RAPTOR vs SimVP on low-resolution KTH | video predictor · KTH 10->30 | PSNR: 33.7 -> 32.0 PSNR; 0.905 -> 0.912 SSIM | Mixed |
| scale input resolution from 512 to 1024 for RAPTOR | RAPTOR · UAVid | PSNR: 28.4 -> 19.3 | Hurt |
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.
- SimVP — SimVP: Simpler Yet Better Video Prediction (CVPR 2022) · better on 5 of 6 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
- WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation (NeurIPS 2026 · similarity 0.85)
- UAV3D: A Large-scale 3D Perception Benchmark for Unmanned Aerial Vehicles (NeurIPS 2024 · similarity 0.85)
- M$^2$E-UAV: A Benchmark and Analysis for Onboard Motion-on-Motion Event-Based Tiny UAV Detection (NeurIPS 2026 · similarity 0.85)
- Multiview Aerial Visual RECognition (MAVREC): Can Multi-view Improve Aerial Visual Perception? (CVPR 2024 · similarity 0.85)
- RemDet: Rethinking Efficient Model Design for UAV Object Detection (AAAI 2025 · similarity 0.84)
- Learning Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking (ICML 2024 · similarity 0.84)
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.
