Structured Light Field by Two Projectors Placed in Parallel for High-Speed and Precise 3D Feedback

Article Computer Science, Artificial Intelligence

Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset Transfer

Rene Ranftl et al.

Summary: The success of monocular depth estimation relies on large and diverse training sets. This study proposes tools and methods to mix different datasets and improve the performance of monocular depth estimation.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

添加到收藏夹

Article Optics

High-speed object detection with a single-photon time-of-flight image sensor

German Mora-Martin et al.

Summary: 3D time-of-flight (ToF) imaging is widely used in various fields such as augmented reality (AR), computer interfaces, robotics, and autonomous systems. Single-photon avalanche diodes (SPADs) play a critical role in providing accurate depth data over long distances. By employing convolutional neural networks (CNNs) for high-performance object detection, the limitations of small array sizes and limited lateral resolution can be overcome, enabling the extraction of more information from the image. Outdoor results from a portable SPAD camera system demonstrate the advantages of providing the CNN with full histogram data for object detection, with GPU-accelerated processing leading to fast overall latency suitable for safety-critical computer vision applications.

OPTICS EXPRESS (2021)

添加到收藏夹

Article Optics