A Unified Benchmark for Aerial-Enhanced Autonomous Driving: The KITScenes Aerial Dataset
cs.CV
Submitted: 2026-10-29
Updated: 2026-11-09
Comments: Accepted at the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2027)
Project page: https://kitscenes.com/aerial
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- HRDX: A Large-Scale Vector HD-Map Dataset
- AID4AD: Aerial Image Data for Automated Driving Perception
- AerialFusionMapNet: Online HD Map Construction with Aerial-Onboard BEV Fusion
- The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs