利用汽车大灯投影图案，提升夜间深度估计精度。
LED: Light Enhanced Depth Estimation at Night
- 利用车辆大灯投影的光斑模式增强低光环境下的深度感知。
- 在多个模型上实现显著性能提升，真实与合成数据均有效。
- 适合自动驾驶系统夜间视觉感知优化，尤其无激光雷达场景。
夜间基于摄像头的深度估计极具挑战性，尤其在自动驾驶中，精准深度感知对安全导航至关重要。现有基于日间数据训练的模型在缺乏精确但昂贵的激光雷达时表现不佳。即使大规模视觉基础模型在低光照下也不可靠。本文提出轻量级光增强深度（LED）方法，通过利用现代车辆高清大灯投射的光图案，显著提升低光环境下的深度估计可靠性。LED在多种架构（编码器-解码器、Adabins、DepthFormer、Depth Anything V2）上均取得显著性能提升，涵盖合成与真实数据集。此外，性能提升不仅限于被照亮区域，表明整体场景理解能力得到增强。最后，我们发布了夜间合成驾驶数据集（Nighttime Synthetic Drive Dataset），包含49,990张全面标注的逼真夜间图像。
原文摘要 · Abstract (English)
Nighttime camera-based depth estimation is a highly challenging task, especially for autonomous driving applications, where accurate depth perception is essential for ensuring safe navigation. Models trained on daytime data often fail in the absence of precise but costly LiDAR. Even vision foundation models trained on large amounts of data are unreliable in low-light conditions. In this work, we aim to improve the reliability of perception systems at night time. To this end, we introduce Light Enhanced Depth (LED), a novel, cost-effective approach that significantly improves depth estimation in low-light environments by harnessing a pattern projected by high definition headlights available in modern vehicles. LED leads to significant performance boosts across multiple depth-estimation architectures (encoder-decoder, Adabins, DepthFormer, Depth Anything V2) both on synthetic and real datasets. Furthermore, increased performances beyond illuminated areas reveal a holistic enhancement in scene understanding. Finally, we release the Nighttime Synthetic Drive Dataset, a synthetic and photo-realistic nighttime dataset, which comprises 49,990 comprehensively annotated images.
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。