Oxygen Reduction Reaction Activity of Fe-based Dual-Atom Catalysts with Different Local Configurations via Graph Neural Representation

The performance of proton exchange membrane fuel cells depends heavily on the oxygen reduction reaction(ORR)at the cathode,for which platinum-based catalysts are currently the standard.The high cost and limited availability of platinum have driven the search for alternative catalysts.While FeN4 single-atom catalysts have shown promising potential,their ORR activity needs to be further enhanced.In contrast,dual-atom catalysts(DACs)offer not only higher metal loading but also the ability to break the ORR scaling relations.However,the diverse local structures and tunable coordination environments of DACs create a vast chemical space,making large-scale computational screening challenging.In this study,we developed a graph neural network(GNN)-based framework to predict the ORR activity of Fe-based DACs,effectively addressing the challenges posed by variations in local catalyst structures.Our model,trained on a dataset of 180 catalysts,accurately predicted the Gibbs free energy of ORR intermediates and overpotentials,and identified 32 DACs with superior catalytic activity compared to FeN4 SAC.This approach not only advances the design of high-performance DACs,but also offers a powerful computational tool that can significantly reduce the time and cost of catalyst development,thereby accelerating the commercialization of fuel cell technologies.

MarkINeRV: A Robust Watermarking Scheme for Neural Representation for Videos Based on Invertible Neural Networks

Recent research advances in implicit neural representation have shown that a wide range of video data distributions are achieved by sharing model weights for Neural Representation for Videos(NeRV).While explicit methods exist for accurately embedding ownership or copyright information in video data,the nascent NeRV framework has yet to address this issue comprehensively.In response,this paper introduces MarkINeRV,a scheme designed to embed watermarking information into video frames using an invertible neural network watermarking approach to protect the copyright of NeRV,which models the embedding and extraction of watermarks as a pair of inverse processes of a reversible network and employs the same network to achieve embedding and extraction of watermarks.It is just that the information flow is in the opposite direction.Additionally,a video frame quality enhancement module is incorporated to mitigate watermarking information losses in the rendering process and the possibility ofmalicious attacks during transmission,ensuring the accurate extraction of watermarking information through the invertible network’s inverse process.This paper evaluates the accuracy,robustness,and invisibility of MarkINeRV through multiple video datasets.The results demonstrate its efficacy in extracting watermarking information for copyright protection of NeRV.MarkINeRV represents a pioneering investigation into copyright issues surrounding NeRV.

Multi-scale hash encoding based neural geometry representation

Recently, neural implicit function-basedrepresentation has attracted more and more attention,and has been widely used to represent surfacesusing differentiable neural networks. However, surfacereconstruction from point clouds or multi-view imagesusing existing neural geometry representations stillsuffer from slow computation and poor accuracy. Toalleviate these issues, we propose a multi-scale hashencoding-based neural geometry representation whicheffectively and efficiently represents the surface asa signed distance field. Our novel neural networkstructure carefully combines low-frequency Fourierposition encoding with multi-scale hash encoding. Theinitialization of the geometry network and geometryfeatures of the rendering module are accordinglyredesigned. Our experiments demonstrate that theproposed representation is at least 10 times faster forreconstructing point clouds with millions of points.It also significantly improves speed and accuracyof multi-view reconstruction. Our code and modelsare available at https://github.com/Dengzhi-USTC/Neural-Geometry-Reconstruction.

NeuPh:scalable and generalizable neural phase retrieval with local conditional neural fields

Deep learning has transformed computational imaging,but traditional pixel-based representations limit their ability to capture continuous multiscale object features.Addressing this gap,we introduce a local conditional neural field(LCNF)framework,which leverages a continuous neural representation to provide flexible object representations.LCNF’s unique capabilities are demonstrated in solving the highly ill-posed phase retrieval problem of multiplexed Fourier ptychographic microscopy.Our network,termed neural phase retrieval(NeuPh),enables continuous-domain resolution-enhanced phase reconstruction,offering scalability,robustness,accuracy,and generalizability that outperform existing methods.NeuPh integrates a local conditional neural representation and a coordinate-based training strategy.We show that NeuPh can accurately reconstruct high-resolution phase images from low-resolution intensity measurements.Furthermore,NeuPh consistently applies continuous object priors and effectively eliminates various phase artifacts,demonstrating robustness even when trained on imperfect datasets.Moreover,NeuPh improves accuracy and generalization compared with existing deep learning models.We further investigate a hybrid training strategy combining both experimental and simulated datasets,elucidating the impact of domain shift between experiment and simulation.Our work underscores the potential of the LCNF framework in solving complex large-scale inverse problems,opening up new possibilities for deep-learning-based imaging techniques.

Odor representation and coding by the mitral/tufted cells in the olfactory bulb

The olfactory bulb(OB)is the first relay station in the olfactory system and functions as a crucial hub.It can represent odor information precisely and accurately in an ever-changing environment.As the only output neurons in the OB,mitral/tufted cells encode information such as odor identity and concentration.Recently,the neural strategies and mechanisms underlying odor representation and encoding in the OB have been investigated extensively.Here we review the main progress on this topic.We first review the neurons and circuits involved in odor representation,including the different cell types in the OB and the neural circuits within and beyond the OB.We will then discuss how two different coding strategies—spatial coding and temporal coding—work in the rodent OB.Finally,we discuss potential future directions for this research topic.Overall,this review provides a comprehensive description of our current understanding of how odor information is represented and encoded by mitral/tufted cells in the OB.

Neural 3D reconstruction from sparse views using geometric priors

Sparse view 3D reconstruction has attracted increasing attention with the development of neural implicit 3D representation.Existing methods usually only make use of 2D views,requiring a dense set of input views for accurate 3D reconstruction.In this paper,we show that accurate 3D reconstruction can be achieved by incorporating geometric priors into neural implicit 3D reconstruction.Our method adopts the signed distance function as the 3D representation,and learns a generalizable 3D surface reconstruction model from sparse views.Specifically,we build a more effective and sparse feature volume from the input views by using corresponding depth maps,which can be provided by depth sensors or directly predicted from the input views.We recover better geometric details by imposing both depth and surface normal constraints in addition to the color loss when training the neural implicit 3D representation.Experiments demonstrate that our method both outperforms state-of-the-art approaches,and achieves good generalizability.

Towards efficient and photorealistic 3D human reconstruction: A brief survey

Reconstructing 3D digital models of humans from sensory data is a long-standing problem in computer vision and graphics with a variety of applications in VR/AR,film production,and human–computer interaction,etc.While a huge amount of effort has been devoted to developing various capture hardware and reconstruction algorithms,traditional reconstruction pipelines may still suffer from high-cost capture systems and tedious capture processes,which prevent them from being easily accessible.Moreover,the dedicatedly hand-crafted pipelines are prone to reconstruction artifacts,resulting in limited visual quality.To solve these challenges,the recent trend in this area is to use deep neural networks to improve reconstruction efficiency and robustness by learning human priors from existing data.Neural network-based implicit functions have been also shown to be a favorable 3D representation compared to traditional forms like meshes and voxels.Furthermore,neural rendering has emerged as a powerful tool to achieve highly photorealistic modeling and re-rendering of humans by end-to-end optimizing the visual quality of output images.In this article,we will briefly review these advances in this fast-developing field,discuss the advantages and limitations of different approaches,and finally,share some thoughts on future research directions.

MDISN:Learning multiscale deformed implicit fields from single images

We present a multiscale deformed implicit surface network(MDISN)to reconstruct 3D objects from single images by adapting the implicit surface of the target object from coarse to fine to the input image.The basic idea is to optimize the implicit surface according to the change of consecutive feature maps from the input image.And with multi-resolution feature maps,the implicit field is refined progressively,such that lower resolutions outline the main object components,and higher resolutions reveal fine-grained geometric details.To better explore the changes in feature maps,we devise a simple field deformation module that receives two consecutive feature maps to refine the implicit field with finer geometric details.Experimental results on both synthetic and real-world datasets demonstrate the superiority of the proposed method compared to state-of-the-art methods.