Brief

Researchers have developed a new method for camera pose estimation using visible light positioning (VLP) with Lamé curve-shaped LEDs. This approach, termed LC-VLP, aims to reduce the number of LEDs required by treating various LED shapes as unified Lamé curves. The system involves LEDs broadcasting their parameters, which a camera-equipped receiver captures to estimate its pose through a nonlinear least-squares problem. A novel correspondence-free PnP algorithm provides reliable initialization, and experiments show LC-VLP outperforms existing methods, achieving position errors reduced by over 30% and an average position accuracy of less than 4 cm. AI

Researchers have introduced Depth2Pose, a new benchmark for evaluating monocular depth estimation models. This framework assesses depth quality based on the accuracy of camera pose estimation, a more practical metric for downstream tasks like visual localization and SLAM. Unlike traditional methods requiring expensive per-pixel depth data, Depth2Pose utilizes readily available camera poses, enabling evaluation in challenging environments where ground-truth depth is difficult to acquire. The accompanying D2P dataset features scenes outside the typical distribution of existing training data, highlighting potential generalization issues with current models. AI