用动态灯光提升夜间视觉，让白天模型零样本适配黑夜
LiDAS: Lighting-driven Dynamic Active Sensing for Nighttime Perception
- 根据目标区域动态调节灯光分布，不均匀照明
- 实测比普通近光灯高18.7%的mAP50和5.0%的mIoU
- 节能40%的同时增强感知，适合自动驾驶场景
夜间环境对基于摄像头的感知带来巨大挑战，现有方法被动依赖场景光照。我们提出光照驱动的动态主动感知系统LiDAS，将现成视觉模型与高清大灯结合，构建闭环主动照明系统。不同于均匀增亮，LiDAS动态预测最优光照场，通过减少空区域光照、集中投向物体区域来提升下游感知性能。该系统使白天训练的模型在零样本条件下实现夜间泛化。在合成数据上训练后，直接部署于真实闭环驾驶场景，相比标准近光灯，在相同功耗下实现+18.7% mAP50和+5.0% mIoU，并在保持性能的同时降低40%能耗。LiDAS可与领域泛化方法互补，进一步提升鲁棒性而无需重新训练。通过将现有大灯转化为主动视觉执行器，提供了低成本、高鲁棒性的夜间感知解决方案。
原文摘要 · Abstract (English)
Nighttime environments pose significant challenges for camera-based perception, as existing methods passively rely on the scene lighting. We introduce Lighting-driven Dynamic Active Sensing (LiDAS), a closed-loop active illumination system that combines off-the-shelf visual perception models with high-definition headlights. Rather than uniformly brightening the scene, LiDAS dynamically predicts an optimal illumination field that maximizes downstream perception performance, i.e., decreasing light on empty areas to reallocate it on object regions. LiDAS enables zero-shot nighttime generalization of daytime-trained models through adaptive illumination control. Trained on synthetic data and deployed zero-shot in real-world closed-loop driving scenarios, LiDAS enables +18.7% mAP50 and +5.0% mIoU over standard low-beam at equal power. It maintains performances while reducing energy use by 40%. LiDAS complements domain-generalization methods, further strengthening robustness without retraining. By turning readily available headlights into active vision actuators, LiDAS offers a cost-effective solution to robust nighttime perception.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。