KiC4R
收藏资源简介:
KiC4R是一个合成的低光照数据集,由上海大学的研究团队创建,旨在为视觉里程计(VO)框架在挑战性环境中的训练和评估提供支持。该数据集包含多种光照条件,模拟了夜间或光照不足的场景,以帮助提升VO算法在低光照环境下的性能。数据集通过CARLA模拟器生成,适用于自动驾驶和机器人导航等领域,旨在解决低光照条件下视觉里程计的精度和鲁棒性问题。
KiC4R is a synthetic low-light dataset developed by the research team from Shanghai University. It is designed to support the training and evaluation of visual odometry (VO) frameworks in challenging environments. This dataset encompasses diverse lighting conditions, simulating nighttime or insufficient-light scenarios to enhance the performance of VO algorithms in low-light environments. Generated using the CARLA simulator, the dataset is applicable to fields including autonomous driving and robotic navigation, and aims to address the accuracy and robustness issues of visual odometry under low-light conditions.

- 1BRIGHT-VO: Brightness-Guided Hybrid Transformer for Visual Odometry with Multi-modality Refinement Module上海大学 · 2025年



