Free space optical (FSO) communication is a promising solution for next-generation communication networks. Atmospheric turbulence, however, severely degrades its performance. We thus propose a novel turbulence-robust end-to-end FSO communication system (TRFSO) that performs joint training across the entire transmission process from source to transmission channel to destination. To introduce physical FSO channel impairments into the training loop, we developed a bidirectional long short-term memory (BiLSTM)-based FSO channel model. Through end-to-end joint training, the system achieved high quality and robust transmission under dynamic atmospheric turbulence. Trained on experimental data collected over a physical FSO link under varying turbulence conditions, the proposed model accurately reproduced real-world channel distortions, achieving a minimum Kullback–Leibler (KL) divergence of 0.0019 nats in amplitude distribution matching. Our experimental results revealed that TRFSO significantly outperformed conventional separate coding modulation schemes in FSO links. Moreover, under strong turbulence, TRFSO achieved a 3.5 dB gain in average multi-scale structural similarity (MS-SSIM) compared with the same network architecture trained without the channel model.

The HEVC standard, designed to outperform H.264/AVC in compression efficiency, incorporates several advanced techniques in intra coding, including coding tree units (CTUs) and an expanded set of 35 prediction modes per prediction unit (PU). While these innovations enhance coding performance, they also escalate computational complexity. We present a fast intra-mode decision method for HEVC to lower complexity. First, the algorithm integrates the grid design characteristics of intra-prediction, tailoring texture gradient prediction angles for coding units (CUs) of varying sizes. Second, a dynamic preselection method leveraging the cumulative energy of texture gradients and the Most Probable Mode (MPM) mechanism is employed to efficiently filter candidate prediction modes. Experimental results show the proposed algorithm improves coding efficiency by$\mathbf{2 2. 3 \%}$over HM18.0, with only$\mathbf{1. 6 \%}$average bitrate increase.

Communication enables the expansion of human visual perception beyond the limitations of time and distance, while computational imaging overcomes the constraints of depth and breadth. Although impressive achievements have been witnessed with the two types of technologies, the occlusive information flow between the two domains is a bottleneck hindering their ulterior progression. Herein, we propose a novel framework that integrates communication and computational imaging (ICCI) to break through the inherent isolation between communication and computational imaging for remote visual perception. By jointly considering the acquisition and transmission of remote visual information, the ICCI framework performs a full-link information transfer optimization, aiming to minimize information loss from the generation of the information source to the execution of the final vision tasks. We conduct numerical analysis and experiments to demonstrate the ICCI framework by integrating communication systems and snapshot compressive imaging systems. Compared with straightforward combination schemes, which sequentially execute sensing and transmitting, the ICCI scheme shows greater robustness against channel noise and impairments while achieving higher data compression. Moreover, an 80 km 27-band hyperspectral video perception with a rate of 30 fps is experimentally achieved. This new ICCI remote perception paradigm offers a high-efficiency solution for various real-time computer vision tasks.

Achieving efficient point cloud (PC) transmission is a fundamental requirement for immersive holographic-type communication. However, traditional optical fiber communication (TOFC), based on separated coding modulation for PC transmission, faces challenges related to massive data transmission and heavy computational resource requirements. To achieve lightweight and efficient PC transmission, we propose and experimentally demonstrate a joint coding-modulation optical fiber communication system for PC transmission (JCMPC). A joint encoding-modulation (JEM) network based on 3D convolution is designed to encode the PC into symbols for transmission directly. At the receiver, a joint decoding-demodulation (JDD) network is used to reconstruct the signals transmitted through the communication channel into the received PC. The experimental results indicate that the proposed JCMPC outperforms transmission schemes based on separate coding modulation and exhibits gradual performance degradation with the deterioration of channel conditions. We evaluate the decoding computational complexity of our proposed JCMPC scheme against the separate transmission schemes using Geometry-based Point Cloud Compression (G-PCC) and Low-Density Parity-Check (LDPC) codes. The results demonstrate that JCMPC reduces the decoding computational operations by over 80% compared to G-PCC+LDPC.

Machine learning is regarded as an attractive solution for soft failure management in optical networks; however, the performance of trained models working on unseen data is of growing concern, due to scarce historical data and high training costs. Hence, the issues of reducing training data and improving generalization have received considerable attention. In this paper, a soft failure detection (SFD) and identification scheme is proposed based on digital residual spectrum that leverages auto-encoder (AE) and support vector machine. The digital residual spectrum acquired by the coherent receiver is computed by subtracting the averaged spectrum of multiple normal digital spectra from the digital spectrum. The scheme features: (i) high generalization, i.e., a model trained for a specific transmission setup performs well in other setups with different fiber lengths; (ii) low cost, i.e., the digital residual spectrum is easily obtained from a coherent receiver without additional hardware; and (iii) easy training, i.e., only normal samples are needed to train the SFD model (less pressure on the collection of rare soft-failure data). Using the model trained for any specific setup, we demonstrated an area under the curve and identification accuracy above 99.24% and 96.45%, respectively, for five experimental setups.

We consider using untrained neural networks to solve the reconstruction problem of snapshot compressive imaging (SCI), which uses a two-dimensional (2D) detector to capture a high-dimensional (usually 3D) data-cube in a compressed manner. Various SCI systems have been built in recent years to capture data such as high-speed videos, hyperspectral images, and the state-of-the-art reconstruction is obtained by the deep neural networks. However, most of these networks are trained in an end-to-end manner by a large amount of corpus with sometimes simulated ground truth, measurement pairs. In this paper, inspired by the untrained neural networks such as deep image priors (DIP) and deep decoders, we develop a framework by integrating DIP into the plug-and-play regime, leading to a self-supervised network for spectral SCI reconstruction. Extensive synthetic and real data results show that the proposed algorithm without training is capable of achieving competitive results to the training based networks. Furthermore, by integrating the proposed method with a pre-trained deep denoising prior, we have achieved state-of-the-art results. Our code is available at https://github.com/mengziyi64/CASSI-Self-Supervised.

Many neuromorphic chips now include on-chip, digitally programmable bias generator circuits. So far, precision of these generated biases has been designed by transistor sizing and circuit design to ensure tolerable statistical variance due to threshold mismatch. This paper reports the use of an integrated measurement circuit based on spiking neuron and a scheme for calibrating each chip set of biases against the smallest of all the biases from that chip. That way, the averaging across individual biases improves overall matching both within a chip and across chips. This paper includes measurements of generated biases, the method for remapping bias values towards more uniform values, and measurements across 5 sample chips. With the method presented in this paper, 1s mismatch of subthreshold currents is decreased by at least a factor of 3. The firmware implementation completes calibration in about a minute and uses about 1kB of flash storage of calibration data.