LED: Light Enhanced Depth Estimation at Night
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. We aim to improve the reliability of perception systems at night time, where models trained on daytime data often fail in the absence of precise but costly LiDAR sensors. In this work, 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) 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 new synthetic and photo-realistic nighttime dataset, which comprises 49,990 comprehensively annotated images.
Code (1)
Tasks
Autonomous DrivingDecoderDepth EstimationScene UnderstandingSimilar Papers 제목 키워드 기반
LAA-Net: A Physical-prior-knowledge Based Network for Robust Nighttime Depth Estimation
Existing self-supervised monocular depth estimation (MDE) models attempt to improve nighttime performance by using GANs to transfer nighttime images into their daytime versions. However, this can introduce inconsistencie…
Depth EstimationMonocular Depth EstimationDepthDark: Robust Monocular Depth Estimation for Low-Light Environments
In recent years, foundation models for monocular depth estimation have received increasing attention. Current methods mainly address typical daylight conditions, but their effectiveness notably decreases in low-light env…
parameter-efficient fine-tuningMonocular Depth EstimationNighttime Stereo Depth Estimation using Joint Translation-Stereo Learning: Light Effects and Uninformative Regions
Nighttime stereo depth estimation is still challenging, as assumptions associated with daytime lighting conditions do not hold any longer. Nighttime is not only about low-light and dense noise, but also about glow/glare,…
Depth EstimationStereo Depth EstimationTranslationSelf-Supervised Monocular Depth Estimation in the Dark: Towards Data Distribution Compensation
Nighttime self-supervised monocular depth estimation has received increasing attention in recent years. However, using night images for self-supervision is unreliable because the photometric consistency assumption is usu…
Depth EstimationDomain AdaptationMonocular Depth EstimationEVEN: An Event-Based Framework for Monocular Depth Estimation at Adverse Night Conditions
Accurate depth estimation under adverse night conditions has practical impact and applications, such as on autonomous driving and rescue robots. In this work, we studied monocular depth estimation at night time in which …
Autonomous DrivingDepth EstimationMonocular Depth Estimation