80 × 120 AI-enhanced LiDAR system based on a lightweight intensity-RGB-dToF sensor fusion neural network deployed on an edge device.

Collecting higher-quality three-dimensional points-cloud data in various scenarios practically and robustly has led to a strong demand for such dToF-based LiDAR systems with higher ambient noise rejection ability and limited optical power consumption, which is a sharp conflict. To alleviate such a clash, an idea of utilizing a strong ambient noise rejection ability of intensity and RGB images is proposed, based on which a lightweight CNN is newly, to the best of our knowledge, designed, achieving a state-of-the-art performance even with 90 × less inference time and 480 × fewer FLOPs. With such net deployed on edge devices, a complete AI-LiDAR system is presented, showing a 100 × fewer signal photon demand in simulation experiments when creating depth images of the same quality.

Dual-mode LiDAR SoC with an on-chip interframe filter and common optical platform design for keystone correction and auto-focus.

This paper presents an innovative methodology that incorporates direct time-of-flight technology into intelligent sensing for projectors, along with a lightweight, dual-mode optically integrated LiDAR system. The proposed LiDAR system-on-chip, which utilizes a single-photon avalanche diode and time to digital converter with 0.13 µm bipolar CMOS DMOS technology, integrates an on-chip interframe filter, a common optical platform design, and a lightweight keystone correction assist algorithm.

A 256 × 256 LiDAR Imaging System Based on a 200 mW SPAD-Based SoC with Microlens Array and Lightweight RGB-Guided Depth Completion Neural Network.

Light detection and ranging (LiDAR) technology, a cutting-edge advancement in mobile applications, presents a myriad of compelling use cases, including enhancing low-light photography, capturing and sharing 3D images of fascinating objects, and elevating the overall augmented reality (AR) experience. However, its widespread adoption has been hindered by the prohibitive costs and substantial power consumption associated with its implementation in mobile devices. To surmount these obstacles, this paper proposes a low-power, low-cost, single-photon avalanche detector (SPAD)-based system-on-chip (SoC) which packages the microlens arrays (MLAs) and a lightweight RGB-guided sparse depth imaging completion neural network for 3D LiDAR imaging.

228 × 304 200-mW lidar based on a single-point global-depth d-ToF sensor and RGB-guided super-resolution neural network.

The cutting-edge imaging system exhibits low output resolution and high power consumption, presenting challenges for the RGB-D fusion algorithm. In practical scenarios, aligning the depth map resolution with the RGB image sensor is a crucial requirement. In this Letter, the software and hardware co-design is considered to implement a lidar system based on the monocular RGB 3D imaging algorithm.

Dual pulse repetition rates with high background noise tolerance for memory-efficient SPAD LiDAR.

Single-photon avalanche diode (SPAD) sensors for flash light detection and ranging (LiDAR) typically have high memory overhead. The widely adopted memory-efficient two-step coarse-fine (CF) process suffers from degraded background noise (BGN) tolerance. To alleviate this issue, we propose a dual pulse repetition rate (DPRR) scheme while maintaining a high histogram compression ratio (HCR).

A dToF Ranging Sensor with Accurate Photon Detector Measurements for LiDAR Applications.

Direct time-of-flight (dToF) ranging sensors based on single-photon avalanche diodes (SPADs) have been used as a prominent depth-sensing devices. Time-to-digital converters (TDCs) and histogram builders have become the standard for dToF sensors. However, one of the main current issues is the bin width of the histogram, which limits the accuracy of depth without TDC architecture modifications.

Multi-Scale Histogram-Based Probabilistic Deep Neural Network for Super-Resolution 3D LiDAR Imaging.

LiDAR (Light Detection and Ranging) imaging based on SPAD (Single-Photon Avalanche Diode) technology suffers from severe area penalty for large on-chip histogram peak detection circuits required by the high precision of measured depth values. In this work, a probabilistic estimation-based super-resolution neural network for SPAD imaging that firstly uses temporal multi-scale histograms as inputs is proposed. To reduce the area and cost of on-chip histogram computation, only part of the histogram hardware for calculating the reflected photons is implemented on a chip.

A near-threshold, 0.16 nJ/b OOK-transmitter with 0.18 nJ/b noise-cancelling super-regenerative receiver for the medical implant communications service.

A 0.16 nJ/b MICS transmitter and 0.18 nJ/b super-regenerative receiver are demonstrated, where each is specifically designed to operate in the near-threshold region.