Learning to Restore Compressed Point Cloud Attribute: A Fully Data-Driven Approach and A Rules-Unrolling-Based Optimization.

The emergence of holographic media drives the standardization of Geometry-based Point Cloud Compression (G-PCC) to sustain networked service provisioning. However, G-PCC inevitably introduces visually annoying artifacts, degrading the quality of experience (QoE). This work focuses on restoring G-PCC compressed point cloud attributes, e.g., RGB colors, to which fully data-driven and rules-unrolling-based post-processing filters are studied. At first, as compressed attributes exhibit nested blockiness, we develop a learning-based sample adaptive offset (NeuralSAO), which leverages a neural model using multiscale feature aggregation and embedding to characterize local correlations for quantization error compensation. Later, given statistically Gaussian distributed quantization noise, we suggest the utilization of a bilateral filter with Gaussian kernels to weigh neighbors by jointly considering their geometric and photometric contributions for restoration. Since local signals often present varying distributions, we propose estimating the smoothing parameters of the bilateral filter using an ultra-lightweight neural model. Such a bilateral filter with learnable parameters is called NeuralBF. The proposed NeuralSAO demonstrates the state-of-art restoration quality improvement, e.g., >20% BD-BR (Bjøntegaard delta rate) reduction over G-PCC on solid points clouds. However, NeuralSAO is computationally intensive and may suffer from poor generalization. On the other hand, although NeuralBF only achieves half of the gains of NeuralSAO, it is lightweight and exhibits impressive generalization across various samples. This comparative study between the data-driven large-scale NeuralSAO and the rules-unrolling-based small-scale NeuralBF helps to understand the capacity (i.e., performance, complexity, generalization) of underlying filters in terms of the quality restoration for compressed point cloud attribute.

A Binary Mixture of Emamectin Benzoate and Chlorantraniliprole Supplemented with an Adjuvant Effectively Controls Spodoptera frugiperda.

The fall armyworm (FAW) Spodoptera frugiperda is a notorious pest, causing severe crop damage worldwide and prompting effective prevention and control. Over-reliance on and intensive use of insecticides are prone to leading to the rapid evolution of insecticide resistance, urging rational insecticide application. One effective way of rational insecticide application is to apply insecticides of different modes of action in combination or supplemented with adjuvants. In this study, we assessed the efficacies of two individual insecticides, emamectin benzoate (EB) and chlorantraniliprole (CT), and their mixture, supplemented with and without the oil adjuvant Jijian® to control FAW in laboratory bioassays and a field trial. Both EB and CT showed high toxicities to FAW. The EB × CT mixture at a mass ratio of 9:1 yielded a remarkable synergistic effect, with the co-toxicity coefficient (CTC) being 239.38 and the median lethal concentration (LC50) being 0.177 mg/L. In leaf-spray bioassays, the addition of the adjuvant reduced the LC50 values of both the individual insecticides and the EB × CT mixture by more than 59%, significantly improving the efficacies. The field trial confirmed the synergistic effects of the adjuvant, which reduced the amount of EB × CT mixture by 80%. This study provides an effective and promising insecticide-adjuvant mixture to control S. frugiperda.

Identification of yellow gene family and functional analysis of Spodoptera frugiperda yellow-y by CRISPR/Cas9.

For a devastating agricultural pest, functional genomics promotes the finding of novel technology to control Spodoptera frugiperda, such as the genetics-based strategies. In the present study, 11 yellow genes were identified in Spodoptera frugiperda. The transcriptome analysis showed the tissue-specific expression of part yellow genes, which suggested the importance of yellow genes in some biological processes in S. frugiperda, such as pigmentation. Among these yellow genes, the expression profiles of yellow-y gene showed that it was expressed in all life stages. In order to realize the further study of yellow-y, we employed CRISPR/Cas9 system to knock out this gene. Following knock out, diverse phenotypes were observed, such as color changes in both larvae and adults. Different from the wild-type larvae and adults, G0 mutants were yellowed since hatching. However, no color difference was observed with the pupal cuticle between the wild-type and mutant pupae before the 8th day. On the basis of the single-pair strategy of G0 generation, the yellow-y gene was proved to be a recessive gene. The G1 yellowish larvae with biallelic mutations displayed a relatively longer development period than wild-type, and often generated abnormal pupae and moths. The deletion of yellow-y also resulted in a decline in the fecundity. The results revealed that yellow-y gene was important for S. frugiperda pigmentation, as well as in its development and reproduction. Besides, the present study set up a standard procedure to knock out genes in S. frugiperda, which could be helpful for our understanding some key molecular processes, such as functional roles of detoxification genes as insecticide resistance mechanisms or modes of action of insecticides to facilitate the management of this insect pest.