Collaborative Distribution Alignment for 2D image-based 3D shape retrieval

Retrieving 3D shapes with 2D images has become a popular research area nowadays, and a great deal of work has been devoted to reducing the discrepancy between 3D shapes and 2D images to improve retrieval performance. However, most approaches ignore the semantic information and decision boundaries of the two domains, and cannot achieve both domain alignment and category alignment in one module. In this paper, a novel Collaborative Distribution Alignment (CDA) model is developed to address the above existing challenges. Specifically, we first adopt a dual-stream CNN, following a similarity guided constraint module, to generate discriminative embeddings for input 2D images and 3D shapes (described as multiple views). Subsequently, we explicitly introduce a joint domain-class alignment module to dynamically learn a class-discriminative and domain-agnostic feature space, which can narrow the distance between 2D image and 3D shape instances of the same underlying category, while pushing apart the instances from different categories. Furthermore, we apply a decision boundary refinement module to avoid generating class-ambiguity embeddings by dynamically adjusting inconsistencies between two discriminators. Extensive experiments and evaluations on two challenging benchmarks, MI3DOR and MI3DOR-2, demonstrate the superiority of the proposed CDA method for 2D image-based 3D shape retrieval task.     

Multi-scale and multi-patch transformer for sandstorm image enhancement

Sandstorm is a meteorological phenomenon common in arid and semi-arid regions. A sandstorm can carry large volumes of sand unexpectedly, which leads to severe color deviations and significantly degraded visibility when an image is taken in such a scenario. However, existing image enhancement methods cannot enhance sandstorm images well due to the challenging degradations and the scarcity of sandstorm training data. In this paper, we propose a Transformer with rotary position embedding to perform sandstorm image enhancement via building multi-scale and multi-patch dependencies. Our key insights in this work are 1) a multi-scale Transformer can globally eliminate the color deviations of sandstorm images via aggregating global information, 2) a multi-patch Transformer can recover local details well via learning the spatial variant degradations, and 3) a U-shape Transformer with rotary position embedding as the core unit of multi-scale and multi-patch Transformer can effectively build the long-range dependencies. We also contribute a real-world Sandstorm Image Enhancement (SIE) dataset including 1,400 sandstorm images with different degrees of degradations and various scenes. Experiments performed on synthetic images and real-world sandstorm images demonstrate that our proposed method not only obtains visually pleasing results but also outperforms state-of-the-art methods qualitatively and quantitatively.     

高光谱成像用高帧频CMOS图像传感器北大核心

针对高帧频、全局曝光和光谱平坦等成像应用需求,设计了一款高光谱成像用CMOS图像传感器。其光敏元采用PN型光电二极管,读出电路采用5T像素结构。采用列读出电路以及高速多通道模拟信号并行读出的设计方案来获得低像素固定图像噪声(FPN)和非均匀性抑制。芯片采用ASMC 0.35μm三层金属两层多晶硅标准CMOS工艺流片,为了抑制光电二极管的光谱干涉效应,后续进行了光谱平坦化VAE特殊工艺,并对器件的光电性能进行了测试评估。电路测试结果符合理论设计预期,成像效果良好,像素具备积分可调和全局快门功能,最终实现的像素规模为512×256,像元尺寸为30μm×30μm,最大满阱电子为400 ke^(-),FPN小于0.2%,动态范围为72 dB,帧频为450 f/s,相邻10 nm波段范围内量子效率相差小于10%,可满足高光谱成像系统对CMOS成像器件的要求。     

基于改进残差特征蒸馏的轻量级超分辨率网络

基于深度学习的图像超分辨率算法通常采用递归的方式或参数共享的策略来减少网络参数，这将增加网络的深度，使得运行网络花费大量的时间，从而很难将模型部署到现实生活中。为了解决上述问题，本文设计一种轻量级超分辨率网络，对中间特征的关联性及重要性进行学习，且在重建部分结合高分辨率图像的特征信息。首先，引入层间注意力模块，通过考虑层与层之间的相关性，自适应地分配重要层次特征的权重。其次，使用增强重建模块提取高分辨率图像中更精细的特征信息，以此得到更加清晰的重建图片。通过大量的对比实验表明，本文设计的网络与其他轻量级模型相比，有更小的网络参数量，并且在重建精度和视觉效果上都有一定的提升。     

基于可供性的文化意象交互式智能音箱设计研究

目的 探索将文化民俗有效融入现代产品中的技术思路，保留并延续中华传统文化的生命力，有助于提升用户体验。方法 分析可供性与文化意象之间的主客观互通性;挖掘交互式智能音箱中的可供性触点;构建形态、感官、认知及情境四类可供性的设计框架;以楚文化意象为例进行设计实践，对智能音箱的产品造型与交互操作方式进行设计，并进行设计评价。结果 在可供性理论指导下的楚文化意象交互式智能音箱产品外观及交互体验设计较好地满足了设计目标和用户需求。结论 可供性有助于文化意象的正确提取与转化，可将意象抽象为具有实际意义的设计要素，帮助用户在生理与认知两个层面理解产品的使用方法，同时进一步回味、体验文化内涵和文化精髓。     

Simply constructed highly dispersed cobalt nanoparticles in diverse N-doped graphitic carbon with remarkable performances for water electrolysis

Metal/carbon composite materials are highly promising electrocatalysts for water electrolysis. In this work, three composites of metal cobalt nanoparticles highly dispersed in N-doped carbon materials were facilely constructed by pyrolysis of different phenylenediamine based Schiff base-Co complexes (PDBs). Interestingly, the composites derived from PDBs based on different phenylenediamine exhibited different morphologies. The superior case is that rodlike composite catalyst was derived from o-phenylenediamine based PDBs. The obtained catalyst exhibited remarkable performances for both cathodic hydrogen evolution reaction (HER) and anodic oxygen evolution reaction (OER), as well as overall water electrolysis. Only 172 and 289 mV of overpotentials and 1.57 V of cell voltage were exhibited at 10 mA cm^?2 for HER, OER and water splitting in 1.0 M KOH, respectively. The catalyst also displayed robust stability and high Faraday efficiency, and thus are potential high-performance catalyst for commercial water electrolysis.     

Experimental study on uplift behavior of shallow anchor plates in geogrid-reinforced soil

Geogrid reinforcement can significantly improve the uplift bearing capacity of anchor plates. However, the failure mechanism of anchor plates in reinforced soil and the contribution of geogrids need further investigation. This paper presents an experimental study on the anchor uplift behavior in geogrid-reinforced soil using particle image velocimetry (PIV) and the high-resolution optical frequency domain reflectometry (OFDR). A series of model tests were performed to identify the relationship between the failure mechanism and various factors, such as anchor embedment ratio, number of geogrid layers, and their location. The test results indicate that soil deformation and the uplift resistance of anchor plates are substantially influenced by anchor embedment ratio and location of geogrids, whereas the number of geogrid layers has limited influence. In reinforced soil, increasing the embedment ratio greatly improves the ultimate bearing capacities of anchor plates and affects the interlock between the soil and geogrids. As the embedment depth increases, the failure surfaces gradually change from a vertical slip surface to a bulb-shaped surface that is limited within the soil. The strain monitoring data shows that the deformations of geogrids are symmetrical, and the peak strains of geogrids can characterize the reinforcing effects.     

Accelerating BPC-PaCo through Visually Lossless Techniques

Fast image codecs are a current need in applications that deal with large amounts of images. Graphics Processing Units (GPUs) are suitable processors to speed up most kinds of algorithms, especially when they allow fine-grain parallelism. Bitplane Coding with Parallel Coefficient processing (BPC-PaCo) is a recently proposed algorithm for the core stage of wavelet-based image codecs tailored for the highly parallel architectures of GPUs. This algorithm provides complexity scalability to allow faster execution at the expense of coding efficiency. Its main drawback is that the speedup and loss in image quality is controlled only roughly, resulting in visible distortion at low and medium rates. This paper addresses this issue by integrating techniques of visually lossless coding into BPC-PaCo. The resulting method minimizes the visual distortion introduced in the compressed file, obtaining higher-quality images to a human observer. Experimental results also indicate 12% speedups with respect to BPC-PaCo.     

No-Reference Video Quality Assessment using novel hybrid features and two-stage hybrid regression for score level fusion

This paper presents a novel No-Reference Video Quality Assessment (NR-VQA) model that utilizes proposed 3D steerable wavelet transform-based Natural Video Statistics (NVS) features as well as human perceptual features. Additionally, we proposed a novel two-stage regression scheme that significantly improves the overall performance of quality estimation. In the first stage, transform-based NVS and human perceptual features are separately passed through the proposed hybrid regression scheme: Support Vector Regression (SVR) followed by Polynomial curve fitting. The two visual quality scores predicted from the first stage are then used as features for the similar second stage. This predicts the final quality scores of distorted videos by achieving score level fusion. Extensive experiments were conducted using five authentic and four synthetic distortion databases. Experimental results demonstrate that the proposed method outperforms other published state-of-the-art benchmark methods on synthetic distortion databases and is among the top performers on authentic distortion databases. The source code is available at https://github.com/anishVNIT/two-stage-vqa.