Accurately localizing and segmenting obscured objects from faint light patterns beyond the field of view is highly challenging due to multiple scattering and medium-induced perturbations. Most existing methods, based on real-valued modeling or local convolutional operations, are inadequate for capturing the underlying physics of coherent light propagation. Moreover, under low signal-to-noise conditions, these methods often converge to non-physical solutions, severely compromising the stability and reliability of the observation. To address these challenges, we propose a novel physics-driven Wavefront Propagating Compensation Network (WavePCNet) to simulate wavefront propagation and enhance the perception of obscured objects. This WavePCNet integrates the Tri-Phase Wavefront Complex-Propagation Reprojection (TriWCP) to incorporate complex amplitude transfer operators to precisely constrain coherent propagation behavior, along with a momentum memory mechanism to effectively suppress the accumulation of perturbations. Additionally, a High-frequency Cross-layer Compensation Enhancement is introduced to construct frequency-selective pathways with multi-scale receptive fields and dynamically models structural consistency across layers, further boosting the model’s robustness and interpretability under complex environmental conditions. Extensive experiments conducted on four physically collected datasets demonstrate that WavePCNet consistently outperforms state-of-the-art methods across both accuracy and robustness.

To overcome the 180° coverage limitation of conventional reflective Reconfigurable Intelligent Surfaces (RIS) in challenging Non-Line-of-Sight (NLoS) environments like underground coal mines, this paper proposes the deployment of a Simultaneously Transmitting and Reflecting RIS (STAR-RIS). The STAR-RIS achieves full 360° signal coverage, effectively addressing the spatial constraints of complex tunnel topologies. Furthermore, we introduce a “Position-Flexible” approach, where the entire panel’s location is dynamically adjusted to maximize the average sum-rate across wideband OFDM subcarriers. By exploiting frequency diversity, the proposed system effectively combats the severe frequency-selective fading inherent in multipath-rich mine tunnels. This holistic movement strategy is specifically designed to enhance hardware reliability in harsh, dust-prone mining conditions by mitigating failure risks associated with complex element-wise mechanical actuation. We formulate a joint optimization problem involving broadband active beamforming, passive phase shifts, and the STAR-RIS coordinates. To solve this non-convex problem, an Alternating Optimization (AO) algorithm is developed. Specifically, the STAR-RIS location is optimized via Projected Gradient Ascent (PGA), while the beamforming and phase-shift coefficients are refined using Successive Convex Approximation (SCA) and Semidefinite Relaxation (SDR). Simulation results confirm that the proposed system significantly improves the sum rate, validating its effectiveness for robust underground wireless connectivity.

Salient object detection (SOD) is fundamental to computer vision, yet deep learning approaches often suffer from high computational costs, limiting deployment on resource-constrained devices. We propose a Lightweight Multi-scale Weight Pruning Network (LMWP-Net) to balance high performance with low complexity. LMWP-Net employs an encoder–decoder architecture featuring two key components: a Multi-scale Weight Pruning Module (MWPM) for efficient feature extraction and redundancy reduction, and a Multi-scale Attention Fusion Module (MAFM) for effective integration via attention mechanisms. Extensive experiments on public datasets demonstrate that LMWP-Net consistently outperforms existing lightweight methods and achieves competitive accuracy against state-of-the-art models. Remarkably, compared to the prominent BANet, LMWP-Net achieves a 94.6% reduction in parameters and a 99.5% reduction in FLOPs, validating its superior efficiency and effectiveness for real-time applications. The implemented code is publicly available at https://github.com/IMOP-lab/LMWP-Net .

Ophthalmic diseases such significantly impair the vision of numerous individuals globally. Accurate and real-time 3D reconstruction of macular edema and retinal tears is crucial for improving surgical efficiency and success rates. However, lesion areas often exhibit considerable noise and high heterogeneity, and the imaging devices employed may introduce electronic noise and artifacts. Current 2D medical image segmentation techniques fail to achieve optimal outcomes. To overcome these challenges, we propose the Tri-Path Fourier-Temporal Modulation Network (TriFTM-Net). TriFTM-Net synergistically integrates spatial, frequency, and spatiotemporal features. This design effectively augments both feature representation and extraction. TriFTM-Net comprises three critical modules: the Tri-Path Spectral Hierarchical Encoder (TPSHE), which amplifies feature representation by integrating tri-path features; the Feature Re-Modulation (FRM), which reduces noise interference and enhances feature extraction; and the Hierarchical Feature Reconstruction Module (HFRM), which improves detail preservation in upsampled images. Comparative analysis with thirteen baseline methods demonstrates that our approach achieves the highest Dice scores, IoU, and Kappa coefficient on the OIMHS dataset.Our code is publicly available at https://github.com/IMOP-lab/TriFTM-Net.

Information retrieved from three dimensions is treated uniformly in CNN-based volumetric segmentation methods. However, such neglect of axial disparities fails to capture true spatio-temporal variations. This paper introduces the volumetric axial disentanglement to address the disparities in spatial information along different axial dimensions. Building on this concept, we propose the Post-Axial Refiner (PaR) module to refine segmentation masks by implementing axial disentanglement on the specific axis of the volumetric medical sequences. As a plug-and-play enhancement to existing volumetric segmentation architecture, PaR further utilizes specialized attention approaches to learn disentangled post-decoding features, enhancing spatial representation and structural detail. Validation on various datasets demonstrates PaR's consistent elevation of segmentation precision and boundary clarity across 11 baselines and different imaging modalities, achieving state-of-the-art performance on multiple datasets. Experimental tests demonstrate the ability of volumetric axial disentanglement to refine the segmentation of volumetric medical images. Code is released at https://github.com/IMOP-lab/PaR-Pytorch.

UV unwrapping flattens 3D surfaces to 2D with minimal distortion, often requiring the complex surface to be decomposed into multiple charts. Although extensively studied, existing UV unwrapping methods frequently struggle with AI-generated meshes, which are typically noisy, bumpy, and poorly conditioned. These methods often produce highly fragmented charts and suboptimal boundaries, introducing artifacts and hindering downstream tasks. We introduce PartUV, a part-based UV unwrapping pipeline that generates significantly fewer, part-aligned charts while maintaining low distortion. Built on top of a recent learning-based part decomposition method PartField, PartUV combines high-level semantic part decomposition with novel geometric heuristics in a top-down recursive framework. It ensures each chart’s distortion remains below a user-specified threshold while minimizing the total number of charts. The pipeline integrates and extends parameterization and packing algorithms, incorporates dedicated handling of non-manifold and degenerate meshes, and is extensively parallelized for efficiency. Evaluated across four diverse datasets—including man-made, CAD, AI-generated, and Common Shapes—PartUV outperforms existing tools and recent neural methods in chart count and seam length, achieves comparable distortion, exhibits high success rates on challenging meshes, and enables new applications like part-specific multi-tiles packing. Code for this paper is at https://github.com/EricWang12/PartUV.

Modeling 3D articulated objects with realistic geometry, textures, and kinematics is essential for a wide range of applications. However, existing optimization-based reconstruction methods often require dense multi-view inputs and expensive per-instance optimization, limiting their scalability. Recent feedforward approaches offer faster alternatives but frequently produce coarse geometry, lack texture reconstruction, and rely on brittle, complex multi-stage pipelines. We introduce LARM, a unified feedforward framework that reconstructs 3D articulated objects from sparse-view images by jointly recovering detailed geometry, realistic textures, and accurate joint structures. LARM extends LVSM—a recent novel view synthesis (NVS) approach for static 3D objects—into the articulated setting by jointly reasoning over camera pose and articulation variation using a transformer-based architecture, enabling scalable and accurate novel view synthesis. In addition, LARM generates auxiliary outputs such as depth maps and part masks to facilitate explicit 3D mesh extraction and joint estimation. Our pipeline eliminates the need for dense supervision and supports high-fidelity reconstruction across diverse object categories. Extensive experiments demonstrate that LARM outperforms state-of-the-art methods in both novel view and state synthesis as well as 3D articulated object reconstruction, generating high-quality meshes that closely adhere to the input images. Code for this paper is at https://github.com/sylviayuan-sy/LARM.

The early detection of ocular disorders, including Graves’ disease, myasthenia gravis, conjunctival hyperemia, conjunctivitis, and keratitis, which critically impair the vision of millions worldwide, necessitates large-scale screening predicated on ocular appearance measurements as a crucial diagnostic component. The emerging Internet of Medical Things (IoMT) introduces new avenues for local clinics to embrace portable and extensive diagnostics. However, the inherent heterogeneity and blurriness of ocular images, compounded by environmental noise, and the computational resource constraint hinder the high-precision diagnostics on IoMT devices. In response to these challenges, a linguistic-guided generative large vision model (LiGu-LVM) has been formulated to assist and enhance the diagnostic capability of IoMT-enabled ocular scanners, integrating a dynamically allocated high-speed quantization system (DAHSQS), a linguistic-guided generative local-isolation module (LiGu), an oculo visio transformatrix segmentum-analytica modulorum (OVT-SAM), and a multiscale recursive attention segmentation engine (MuRASE). DAHSQS enables the flexible aggregation and transmission of patient imagery to shift heavy diagnostic tasks from IoMT-enabled mobile ocular scanners to computational clusters, facilitating rapid facial measurements and preliminary screening via dynamic task allocation and scalable server clusters. The LiGu module employs natural language guidance to generate key image locations, using extensive prior knowledge embedded within linguistic models for precise semantic isolation. OVT-SAM synthesizes multilevel features from the large vision model, extracting intermediate characteristic information and addressing global features alongside deep semantic understanding in natural images collected from IoMT-enabled ocular scanners. MuRASE achieves high-fidelity segmentation of ocular images by incorporating contextual recursive attention mechanisms and skip connections with layer-wise reverse connectivity. Extensive experiments show proposed method surpassing 80% Intersection Over Union (IoU) in ocular semantic segmentation on the CelebA-HQ dataset, achieving an IoU of 82.9%, thus exceeding the performance of existing models by 4.9%.

Multi-view mesh reconstruction has long been a challenging problem in graphics and computer vision. In contrast to recent volumetric rendering methods that generate meshes through post-processing, we propose an end-to-end mesh optimization approach called IMLS-Splatting. Our method leverages the sparsity and flexibility of point clouds to efficiently represent the underlying surface. To achieve this, we introduce a splatting-based differentiable Implicit Moving-Least Squares (IMLS) algorithm that enables the fast conversion of point clouds into SDFs and texture fields, optimizing both mesh reconstruction and rasterization. Additionally, the IMLS representation ensures that the reconstructed SDF and mesh maintain continuity and smoothness without the need for extra regularization. With this efficient pipeline, our method enables the reconstruction of highly detailed meshes in approximately 11 minutes, supporting high-quality rendering and achieving state-of-the-art reconstruction performance. Our code is available at https://github.com/SilenKZYoung/IMLS-Splatting.

We present MovingParts, a NeRF-based method for dynamic scene reconstruction and part discovery. We consider motion as an important cue for identifying parts, that all particles on the same part share the common motion pattern. From the perspective of fluid simulation, existing deformation-based methods for dynamic NeRF can be seen as parameterizing the scene motion under the Eulerian view, i.e., focusing on specific locations in space through which the fluid flows as time passes. However, it is intractable to extract the motion of constituting objects or parts using the Eulerian view representation. In this work, we introduce the dual Lagrangian view and enforce representations under the Eulerian/Lagrangian views to be cycle-consistent. Under the Lagrangian view, we parameterize the scene motion by tracking the trajectory of particles on objects. The Lagrangian view makes it convenient to discover parts by factorizing the scene motion as a composition of part-level rigid motions. Experimentally, our method can achieve fast and high-quality dynamic scene reconstruction from even a single moving camera, and the induced part-based representation allows direct applications of part tracking, animation, 3D scene editing, etc.

Open-world 3D reconstruction models have recently garnered significant attention. However, without sufficient 3D inductive bias, existing methods typically entail expensive training costs and struggle to extract high-quality 3D meshes. In this work, we introduce MeshFormer, a sparse-view reconstruction model that explicitly leverages 3D native structure, input guidance, and training supervision. Specifically, instead of using a triplane representation, we store features in 3D sparse voxels and combine transformers with 3D convolutions to leverage an explicit 3D structure and projective bias. In addition to sparse-view RGB input, we require the network to take input and generate corresponding normal maps. The input normal maps can be predicted by 2D diffusion models, significantly aiding in the guidance and refinement of the geometry's learning. Moreover, by combining Signed Distance Function (SDF) supervision with surface rendering, we directly learn to generate high-quality meshes without the need for complex multi-stage training processes. By incorporating these explicit 3D biases, MeshFormer can be trained efficiently and deliver high-quality textured meshes with fine-grained geometric details. It can also be integrated with 2D diffusion models to enable fast single-image-to-3D and text-to-3D tasks. **Videos are available at https://meshformer3d.github.io/**

As a novel distributed machine learning approach, federated learning (FL) is proposed to train a global model while preserving data privacy. However, some studies manifest that adversaries can still recover private information from the gradients. Differential privacy (DP) is a rigorous mathematical tool to protect records in a database against leakage. It has been widely applied in FL by perturbing the gradients. Nevertheless, while using DP in FL, the convergence performance of the global model is inevitably degraded. In this paper, we implement a DP-based FL scheme, which achieves local DP (LDP) by adding well-designed Gaussian noise on the gradients before clients upload them to the server. After that, we propose two strategies to improve the convergence performance of the DP-based FL. Both methods are realized by modifying the local objective function to limit the effect of LDP noise on convergence without degrading the privacy protection level. We then provide the detailed framework which adopts the LDP scheme and two strategies. The framework on different machine learning models is tested by simulation results, which show that our framework can improve the convergence performance up to 40% faster under different noise compared with other DP-based FL. Finally, we show the theoretical convergence guarantee of our proposed framework by first presenting the expected decrease in the global loss function for one round of training and then providing the upper convergence bound after multiple communication rounds.

We propose TensoIR, a novel inverse rendering approach based on tensor factorization and neural fields. Unlike previous works that use purely MLP-based neural fields, thus suffering from low capacity and high computation costs, we extend TensoRF, a state-of-the-art approach for radiance field modeling, to estimate scene geometry, surface reflectance, and environment illumination from multi-view images captured under unknown lighting conditions. Our approach jointly achieves radiance field reconstruction and physically-based model estimation, leading to photo-realistic novel view synthesis and relighting results. Benefiting from the efficiency and extensibility of the TensoRF-based representation, our method can accurately model secondary shading effects (like shadows and indirect lighting) and generally support input images captured under single or multiple unknown lighting conditions. The low-rank tensor representation allows us to not only achieve fast and compact reconstruction but also better exploit shared information under an arbitrary number of capturing lighting conditions. We demonstrate the superiority of our method to baseline methods qualitatively and quantitatively on various challenging synthetic and real-world scenes.

We address efficient and structure-aware 3D scene representation from images. Nerflets are our key contribution-a set of local neural radiance fields that together represent a scene. Each nerflet maintains its own spatial position, orientation, and extent, within which it contributes to panoptic, density, and radiance reconstructions. By leveraging only photometric and inferred panoptic image supervision, we can directly and jointly optimize the parameters of a set of nerflets so as to form a decomposed representation of the scene, where each object instance is represented by a group of nerflets. During experiments with indoor and outdoor environments, we find that nerflets: (1) fit and approximate the scene more efficiently than traditional global NeRFs, (2) allow the extraction of panoptic and photometric renderings from arbitrary views, and (3) enable tasks rare for NeRFs, such as 3D panoptic segmentation and interactive editing. Our project page.

Due to the sharp growth of employing mobile devices and IoT (Internet of Things) sensors in daily life, tremendous generated or collected data become one of the most valuable assets for not only users but also numerous applications, which provide various services using user data. However, a large portion of such data is possessed by only a few giant companies in a centralized manner. This incurs the concerns of how user data are harnessed and used and who can use such data because of many cases of privacy violence and data leakage. Therefore, in this paper, we propose a decentralized data sharing marketplace using Ethereum to enable users to share their data in a privacy-preserving and self-governing manner. Users can only share parts of the data from their devices they want to share in the marketplace and gain rewards from the bidding of buyers anonymously. Furthermore, a federated learning use case is demonstrated as a privacy-enhanced application of the proposed marketplace to encourage users to share processed data to avoid raw data leakage.

Protein function annotation is one of the most important research topics for revealing the essence of life at molecular level in the post-genome era. Current research shows that integrating multisource data can effectively improve the performance of protein function prediction models. However, the heavy reliance on complex feature engineering and model integration methods limits the development of existing methods. Besides, models based on deep learning only use labeled data in a certain dataset to extract sequence features, thus ignoring a large amount of existing unlabeled sequence data. Here, we propose an end-to-end protein function annotation model named HNetGO, which innovatively uses heterogeneous network to integrate protein sequence similarity and protein-protein interaction network information and combines the pretraining model to extract the semantic features of the protein sequence. In addition, we design an attention-based graph neural network model, which can effectively extract node-level features from heterogeneous networks and predict protein function by measuring the similarity between protein nodes and gene ontology term nodes. Comparative experiments on the human dataset show that HNetGO achieves state-of-the-art performance on cellular component and molecular function branches.

Learning-based stereo methods usually require a large scale dataset with depth, however obtaining accurate depth in the real domain is difficult, but groundtruth depth is readily available in the simulation domain. In this article we propose a new framework, ActiveZero++, which is a mixed domain learning solution for active stereovision systems that requires no real world depth annotation. In the simulation domain, we use a combination of supervised disparity loss and self-supervised loss on a shape primitives dataset. By contrast, in the real domain, we only use self-supervised loss on a dataset that is out-of-distribution from either training simulation data or test real data. To improve the robustness and accuracy of our reprojection loss in hard-to-perceive regions, our method introduces a novel self-supervised loss called temporal IR reprojection. Further, we propose the confidence-based depth completion module, which uses the confidence from the stereo network to identify and improve erroneous areas in depth prediction through depth-normal consistency. Extensive qualitative and quantitative evaluations on real-world data demonstrate state-of-the-art results that can even outperform a commercial depth sensor. Furthermore, our method can significantly narrow the Sim2Real domain gap of depth maps for state-of-the-art learning based 6D pose estimation algorithms.

Protein is the main material basis of living organisms and plays crucial role in life activities. Understanding the function of protein is of great significance for new drug discovery, disease treatment and vaccine development. In recent years, with the widespread application of deep learning in bioinformatics, researchers have proposed many deep learning models to predict protein functions. However, the existing deep learning methods usually only consider protein sequences, and thus cannot effectively integrate multi-source data to annotate protein functions. In this article, we propose the Prot2GO model, which can integrate protein sequence and PPI network data to predict protein functions. We utilize an improved biased random walk algorithm to extract the features of PPI network. For sequence data, we use a convolutional neural network to obtain the local features of the sequence and a recurrent neural network to capture the long-range associations between amino acid residues in protein sequence. Moreover, Prot2GO adopts the attention mechanism to identify protein motifs and structural domains. Experiments show that Prot2GO model achieves the state-of-the-art performance on multiple metrics.

In this article, we focus on the simulation of active stereovision depth sensors, which are popular in both academic and industry communities. Inspired by the underlying mechanism of the sensors, we designed a fully physics-grounded simulation pipeline that includes material acquisition, ray-tracing-based infrared (IR) image rendering, IR noise simulation, and depth estimation. The pipeline is able to generate depth maps with material-dependent error patterns similar to a real depth sensor in real time. We conduct real experiments to show that perception algorithms and reinforcement learning policies trained in our simulation platform could transfer well to the real-world test cases without any fine-tuning. Furthermore, due to the high degree of realism of this simulation, our depth sensor simulator can be used as a convenient testbed to evaluate the algorithm performance in the real world, which will largely reduce the human effort in developing robotic algorithms. The entire pipeline has been integrated into the SAPIEN simulator and is open-sourced to promote the research of vision and robotics communities.

Traditional depth sensors generate accurate real world depth estimates that surpass even the most advanced learning approaches trained only on simulation domains. Since ground truth depth is readily available in the simulation domain but quite difficult to obtain in the real domain, we propose a method that leverages the best of both worlds. In this paper we present a new framework, ActiveZero, which is a mixed domain learning solution for active stereovision systems that requires no real world depth annotation. First, we demonstrate the transferability of our method to out-of-distribution real data by using a mixed domain learning strategy. In the simulation domain, we use a combination of supervised disparity loss and self-supervised losses on a shape primitives dataset. By contrast, in the real domain, we only use self-supervised losses on a dataset that is out-of-distribution from either training simulation data or test real data. Second, our method introduces a novel self-supervised loss called temporal IR reprojection to increase the robustness and accuracy of our reprojections in hard-to-perceive regions. Finally, we show how the method can be trained end-to-end and that each module is important for attaining the end result. Extensive qualitative and quantitative evaluations on real data demonstrate state of the art results that can even beat a commercial depth sensor. The codes of ActiveZero are available at: httis://github.com/haosulab/active_zero.

While NeRF [28] has shown great success for neural reconstruction and rendering, its limited MLP capacity and long per-scene optimization times make it challenging to model large-scale indoor scenes. In contrast, classical 3D reconstruction methods can handle large-scale scenes but do not produce realistic renderings. We propose NeRFusion, a method that combines the advantages of NeRF and TSDF-based fusion techniques to achieve efficient large-scale reconstruction and photo-realistic rendering. We process the input image sequence to predict per-frame local radiance fields via direct network inference. These are then fused using a novel recurrent neural network that incrementally reconstructs a global, sparse scene representation in real-time at 22 fps. This global volume can be further fine-tuned to boost rendering quality. We demonstrate that NeR-Fusionachieves state-of-the-art quality on both large-scale indoor and small-scale object scenes, with substantially faster reconstruction than NeRF and other recent methods.11https://jetd1.github.io/NeRFusion-Web/

Although the interconnection of all things based on 5G and AI has become an incremental trend in all walks of life, its centralized design has many challenges and drawbacks when applied to industrial and life scenarios. In the field of autonomous driving (a.k.a., auto-driving), the centralized vehicle-to-everything (V2X) system depends heavily on the stability of the central node, and there is seldom a mechanism to guarantee the security, stability and timeliness of information in highly dynamic auto-driving scenarios. In this paper, we first design and implement the AIR-RAFT system that supports wireless distributed consensus for IoT. AIR-RAFT is a complete embedded system based on the Raft consensus algorithm and can be potentially installed on auto-driving vehicles. It can not only achieve wireless consensus to ensure the consistency and security of V2X data but also can synchronize the actions among the vehicles in a distributed manner though all cars are not trusted each other. In addition, we originally propose the “selective edge decision layer” for the AIR-RAFT system which can share part of the decision privilege in auto-driving cars. In practical performance evaluations, the AIR-RAFT based auto-driving vehicles stably achieve multi-node (3–7) wireless data consensus and actions synchronization that maintain good working stability within 350 m centered on the leader.

Controllable generative sequence models with the capability to extract and replicate the style of specific examples enable many applications, including narrating audiobooks in different voices, auto-completing and auto-correcting written handwriting, and generating missing training samples for downstream recognition tasks. However, under an unsupervised-style setting, typical training algorithms for controllable sequence generative models suffer from the training-inference mismatch, where the same sample is used as content and style input during training but unpaired samples are given during inference. In this paper, we tackle the training-inference mismatch encountered during unsupervised learning of controllable generative sequence models. The proposed method is simple yet effective, where we use a style transformation module to transfer target style information into an unrelated style input. This method enables training using unpaired content and style samples and thereby mitigate the training-inference mismatch. We apply style equalization to text-to-speech and text-to-handwriting synthesis on three datasets. We conduct thorough evaluation, including both quantitative and qualitative user studies. Our results show that by mitigating the training-inference mismatch with the proposed style equalization, we achieve style replication scores comparable to real data in our user studies.

Since the coronavirus disease 19 (COVID-19) outbreak, the epidemiological analysis has raised a strong requirement for more effective and accurate contact tracing solution. However, the existing contact tracing solutions either lacked the evaluation of tracing proximity or the features used for the tracing proximity evaluation were susceptible to certain negative environmental factors (e.g., body shielding). In this article, we propose a novel distance estimation algorithm based on machine learning for contact tracing: DISTERNING, where we leverage machine learning algorithms including Learning Vector Quantization, Regression, and Deep Feed-forward (DFF) Neural Network, data processing methods, and digital filters to process the Bluetooth signal information collected by the mobile phone for contact distance estimation. A contact tracing scheme based on edge computing is also proposed for algorithm deployment due to the requirements of the computational power. Compared with the existing contact tracing solutions, our algorithm considers the factors that have significant negative influence on the Bluetooth signal for distance estimation in reality. The evaluation results show that when the collected Bluetooth signal is influenced by real-world negative environmental factors, employing our proposed algorithm DISTERNING can keep the accuracy of the estimated distance reliable. The output distance can be combined with some medical models to conduct infection risk assessments.

We present MVSNeRF, a novel neural rendering approach that can efficiently reconstruct neural radiance fields for view synthesis. Unlike prior works on neural radiance fields that consider per-scene optimization on densely captured images, we propose a generic deep neural network that can reconstruct radiance fields from only three nearby input views via fast network inference. Our approach leverages plane-swept cost volumes (widely used in multi-view stereo) for geometry-aware scene reasoning, and combines this with physically based volume rendering for neural radiance field reconstruction. We train our network on real objects in the DTU dataset, and test it on three different datasets to evaluate its effectiveness and generalizability. Our approach can generalize across scenes (even indoor scenes, completely different from our training scenes of objects) and generate realistic view synthesis results using only three input images, significantly outperforming concurrent works on generalizable radiance field reconstruction. Moreover, if dense images are captured, our estimated radiance field representation can be easily fine-tuned; this leads to fast per-scene reconstruction with higher rendering quality and substantially less optimization time than NeRF.

What is the current state-of-the-art for image restoration and enhancement applied to degraded images acquired under less than ideal circumstances? Can the application of such algorithms as a pre-processing step improve image interpretability for manual analysis or automatic visual recognition to classify scene content? While there have been important advances in the area of computational photography to restore or enhance the visual quality of an image, the capabilities of such techniques have not always translated in a useful way to visual recognition tasks. Consequently, there is a pressing need for the development of algorithms that are designed for the joint problem of improving visual appearance and recognition, which will be an enabling factor for the deployment of visual recognition tools in many real-world scenarios. To address this, we introduce the UG$^2$dataset as a large-scale benchmark composed of video imagery captured under challenging conditions, and two enhancement tasks designed to test algorithmic impact on visual quality and automatic object recognition. Furthermore, we propose a set of metrics to evaluate the joint improvement of such tasks as well as individual algorithmic advances, including a novel psychophysics-based evaluation regime for human assessment and a realistic set of quantitative measures for object recognition performance. We introduce six new algorithms for image restoration or enhancement, which were created as part of the IARPA sponsored UG$^2$Challenge workshop held at CVPR 2018. Under the proposed evaluation regime, we present an in-depth analysis of these algorithms and a host of deep learning-based and classic baseline approaches. From the observed results, it is evident that we are in the early days of building a bridge between computational photography and visual recognition, leaving many opportunities for innovation in this area.

Abstract Nowadays, people trade electricity through centralized companies or organizations which is vulnerable to cyber attacks and incapable of coping with increasing demands from stakeholders. In this paper, we propose a new Peer-to-Peer Electricity Blockchain Trading (P2PEBT) system based on the current charging and discharging schemes for electric vehicles (EV) in the smart grid to enable users to participate in the trading process. In order to cope with the current situation of the high volume of EV integration, the proof-of-Benefit (PoB) consensus primitives are proposed for P2PEBT to achieve demand response by providing incentives to balance local electricity demand in the novel blockchain system. PoB is implemented by executing the smart contracts on the Ethereum platform, and the process of achieving the maximal benefits is completed by submitting the transaction in the decentralized network. Security analysis shows that the P2PEBT system is able to manage a potential protection against up to a number of attacks. We demonstrate that the proposed system using the PoB consensus mechanism can achieve lower power fluctuation without requiring a third-party intermediary.

Finding out the functions of protein in life activities precisely is nontrivial, which is the core of current proteomics research. Gene Ontology standardizes the function of protein into a series of GO terms, each of which belongs to exactly one of the three subontologies: Biological Process (BP), Cellular Component (CC), and Molecular Function (MF). The prediction of protein function can be considered as a multi-label classification problem. Traditional methods often spend a lot of costs to extract handcrafted features and plenty of domain knowledge is needed when solving these tasks, while using deep learning technology can overcome these shortcomings. Here, we propose a deep model GONET based on recurrent convolutional neural networks, which annotates protein in an end-to-end manner. Our model combines protein sequences and protein-protein interaction (PPI) network data, and utilizes representation learning to learn distributed representation of proteins to overcome the sparse nature and semantic independence problem. Moreover, we adopt a quite deep CNNRNN-Attention model, which is able to effectively extract high-order features of protein sequences. We have carried out experiments on several datasets, which achieve the state-of-the-art in some metrics compared with the existing competitive methods.

Coverage-based greybox fuzzing (CGF) is a common method utilizing coverage information to guide fuzzing. American Fuzzy Lop (AFL) is one of the most famous CGF fuzzers and has been used to uncover thousands of vulnerabilities in many software. However, AFL has two major drawbacks, which impedes it from boosting path discovery: (1) aggressively growing mutation overhead; (2) ineffective mutation region selection. In this paper, we propose three new approaches to overcome the drawbacks: (1) Interruptible mutation, which uses a hang monitor to avoid unnecessary mutation overhead; (2) Locality-based mutation, which utilizes mutation information in previous rounds to guide fuzzing useful regions in future rounds; (3) Hotspot-aware fuzzing, which exploits a pre-evaluation process to identify metadata and only mutates these regions. We combine these approaches into a tool named AFLTurbo based on AFL 2.52b. Furthermore, the effectiveness of AFLTurbo is evaluated in terms of both path discovery and bug detection on eight programs as well as LAVA-M with state-of-the-art fuzzers. The experimental results manifest that AFLTurbo can find 141%, 101% and 41% more paths, and reveal 14×, 30× and 5× more bugs than AFL, AFLFast and FairFuzz respectively. Additionally, AFLTurbo discovers 20 vulnerabilities, of which 18 are assigned with CVEs.

Abstract Rastegari et al. recently proposed a certificateless signcryption (CL-SC) scheme. They claimed that their scheme is the first secure CL-SC scheme, which captures the known session-specific temporary information security (KSSTIS), in the standard model. In this paper, we point out that their scheme is insecure, which implies that how to construct a secure CL-SC scheme with KSSTIS in the standard model is still an open problem.

We present a comprehensive study and evaluation of existing single image compression artifact removal algorithms using a new 4K resolution benchmark. This benchmark is called the Large-Scale Ideal Ultra high-definition 4K (LIU4K), and it includes including diversified foreground objects and background scenes with rich structures. Compression artifact removal, as a common post-processing technique, aims at alleviating undesirable artifacts, such as blockiness, ringing, and banding caused by quantization and approximation in the compression process. In this work, a systematic listing of the reviewed methods is presented based on their basic models (handcrafted models and deep networks). The main contributions and novelties of these methods are highlighted, and the main development directions are summarized, including architectures, multi-domain sources, signal structures, and new targeted units. Furthermore, based on a unified deep learning configuration (i.e.same training data, loss function, optimization algorithm,etc.), we evaluate recent deep learning-based methods based on diversified evaluation measures. The experimental results show state-of-the-art performance comparisons of existing methods based on both full-reference, non-reference, and task-driven metrics. Our survey gives a comprehensive reference source for future research on single image compression artifact removal and inspires new directions in related fields.

Most previous image matting methods require a roughly-specificed trimap as input, and estimate fractional alpha values for all pixels that are in the unknown region of the trimap. In this paper, we argue that directly estimating the alpha matte from a coarse trimap is a major limitation of previous methods, as this practice tries to address two difficult and inherently different problems at the same time: identifying true blending pixels inside the trimap region, and estimate accurate alpha values for them. We propose AdaMatting, a new end-to-end matting framework that disentangles this problem into two sub-tasks: trimap adaptation and alpha estimation. Trimap adaptation is a pixel-wise classification problem that infers the global structure of the input image by identifying definite foreground, background, and semi-transparent image regions. Alpha estimation is a regression problem that calculates the opacity value of each blended pixel. Our method separately handles these two sub-tasks within a single deep convolutional neural network (CNN). Extensive experiments show that AdaMatting has additional structure awareness and trimap fault-tolerance. Our method achieves the state-of-the-art performance on Adobe Composition-1k dataset both qualitatively and quantitatively. It is also the current best-performing method on the alphamatting.com online evaluation for all commonly-used metrics.

The massive adoption of Electric Vehicles (EVs) requires the grid system to coordinate with a large number of energy transactions, where the current grid network poses vulnerability against the excessive power loads and attacks. The difficulty of an efficient charging/discharging control mechanism lies on the randomness of future events and scalability of the transaction platform. In this paper, a Proof-of-Benefit consensus mechanism with Online benefit generating (ONPoB) algorithm is proposed on the blockchain platform to handle the EV charging/discharging loads to flatten the overall power load fluctuation. It is demonstrated that all EVs can be charged and achieves a best-known competitive ratio of 2.39. The ONPoB consensus mechanism is approved to better accommodate the EV scenario compared with other mechanisms. And the ONPoB algorithm is able to substantially reduce the Power Fluctuation Level (PFL) in comparison with popular scheduling algorithms.

The emergence of blockchain technology brings opportunities for the transactional energy to minimize the time gap and cost in the trading process. This paper proposes a public power exchange service network for Electric Vehicles (EV) to charge and discharge from the power grid. An enhanced novel consensus mechanism Proof-of-Benefit (ePoB) is proposed to improve the protocol security and performance of the electricity exchange system. Furthermore, the benefit number generation algorithm for choosing the leader in the network guarantees the overall power grid network performance by minimizing the load variance. Through theoretical and experimental analysis, the public power exchange system with ePoB consensus protocol achieves higher scalability than Proof- of-Work (PoW) and Paxo-based or BFT-based consensus protocols. Also, it demonstrates that the consensus protocol is capable of withstanding the Sybil attack while achieving lower power load fluctuation level compared with the benchmark.

Device-free or off-body sensing methods, such as Lidar, can be used for location-driven Activities during Daily Life (ADL) recognition without the need for a mobile host such as a human or robot to use on-body location sensors. Because if such an attachment fails, or is not operational (powered up), when such mobile hosts are device free, it still works. Hence, this paper proposes an innovative method for recognizing ADLs using a state-of-art seq2seq Recurrent Neural Network (RNN) model to classify centimeter level accurate location data from a low-cost, 360°rotating 2D Lidar device. We researched, developed, deployed and validated the system. The results indicate that it can provide a centimeter-level localization accuracy of 88% when recognizing 17 targeted location-related daily activities.

In this paper, we propose an access control solution for exchanging Blockchain-based Electronic Medical Records (EMRs) called BBACS (Block-based Access Control Scheme) that includes an access model and an access scheme. Unlike the existing Blockchain-oriented access schemes for EMRs, our access model can omit the agent layer (gateway) in order to authorise users' access with block level granularity, whilst maintaining compatibility with the underlying Blockchain data structure. Furthermore, the authorisation, encryption, and decryption algorithms presented in BBACS dispense with the need to use a public key infrastructure (PKI) and hence cut down the cost of network construction and improve the computational performance. We validated the efficiency (time cost) of local computation and data transmission (over Wi-Fi) for BBACS using a simulation of BBACS against another Blockchain-oriented access control scheme for EMRs called HDG as our baseline. To the best of our knowledge, BBACS is the first Blockchain-oriented access control solution without the need for an agent (or gateway) design, supporting granular authorisation (block level), that has been proposed for secure EMRs management in eHealth.

In this paper, we propose an architecture for Blockchain-based Electronic Medical Records (EMRs) called GAA-FQ (Granular Access Authorisation supporting Flexible Queries) that comprises an access model and an access authorisation scheme. Unlike existing Blockchain schemes, our access model can authorise different levels of granularity of authorisation, whilst maintaining compatibility with the underlying Blockchain data structure. Furthermore, the authorisation, encryption, and decryption algorithms proposed in the GAA-FQ scheme dispense with the need to use a public key infrastructure (PKI) and hence improve the computation performance needed to support more granular and distributed, yet authorised, EMR data queries. We validated the computation performance and transmission efficiency for GAA-FQ using a simulation of GAA-FQ against an access control scheme for EMRs called ESPAC as our baseline that was not designed using a Blockchain. To the best of our knowledge, GAA- FQ is the first Blockchain-oriented access authorisation scheme with granular access control, supporting flexible data queries, that has been proposed for secure EMR information management.

JPEG is one of the most commonly used standards among lossy image compression methods. However, JPEG compression inevitably introduces various kinds of artifacts, especially at high compression rates, which could greatly affect the Quality of Experience (QoE). Recently, convolutional neural network (CNN) based methods have shown excellent performance for removing the JPEG artifacts. Lots of efforts have been made to deepen the CNN s and extract deeper features, while relatively few works pay attention to the receptive field of the network. In this paper, we illustrate that the quality of output images can be significantly improved by enlarging the receptive fields in many cases. One step further, we propose a Dual-domain Multi-scale CNN (DMCNN) to take full advantage of redundancies on both the pixel and DCT domains. Experiments show that DMCNN sets a new state-of-the-art for the task of JPEG artifact removal.

The use of magnetic field (MF) measurements, unlike typical Wi-Fi or Bluetooth positioning measurements, are unaffected by moving humans, providing more time-invariant location information. We present a novel Fast Path Matching algorithm for MF and Inertial sensor measurements, FPM-MI, to localise a person using MF measurements fused with inertial sensor measurements. Our novelty is twofold: it has a reduced computational cost compared to a particle filter algorithm; it has a fast convergence performance, i.e., a person can walk a much shorter distance, about 3 m, to have an arm-span location accuracy. We validated our system in a library, a retail-like building, with multiple metal shelves and pillars, and determined the positioning error to be 1.8 m (90% confidence).

Deploying trusted (private) cloud computing to exchange, store and analyse data from IoT networks has become mainstream. In this paper, we describe a data privacy transmission scheme for IoT data collection, which supports one-way identity authentication and a dual data integrity validation for low resource devices called the Lo-A&DI (Low-resource for IoT 1-way Authentication and Dual Integrity) scheme. Unlike other schemes that use trusted clouds, the Lo-A&DI can be applied to untrusted public clouds while protecting data security and privacy. Unlike other untrusted cloud security schemes, the Lo-A&DI scheme can be used to support end-to-end data security and privacy from low-resource ICT IoT devices. An experimental validation shows that the performance of the Lo-A&DI is much more adaptable for use in resource-constrained IoT devices when compared to a baseline trusted cloud scheme such as one based upon an interactive (2-way) certificate authentication scheme for IoT data exchange.

Recently, Islam and Li proposed the first certificateless signcryption scheme without ephemeral secret leakage (ESL) attack, called leakage-free certificateless signcryption (leakage-free CLSC) scheme. However, we point out in this paper that the confidentiality property is not captured in their proposal. Moreover, our attack adheres to the security model proposed in the original paper. On the other hand, the security models proposed by Islam and Li are insufficient. In fact, the ESL attack is not involved in the security models since the ephemeral secret is not returned to the adversary when CLSC-Signcryption query and Challenge are issued. Finally, we give the amended security models.

BACKGROUND: Complex disease is largely determined by a number of biomolecules interwoven into networks, rather than a single biomolecule. A key but inadequately addressed issue is how to test possible differences of the networks between two groups. Group-level comparison of network properties may shed light on underlying disease mechanisms and benefit the design of drug targets for complex diseases. We therefore proposed a powerful score-based statistic to detect group difference in weighted networks, which simultaneously capture the vertex changes and edge changes. RESULTS: Simulation studies indicated that the proposed network difference measure (NetDifM) was stable and outperformed other methods existed, under various sample sizes and network topology structure. One application to real data about GWAS of leprosy successfully identified the specific gene interaction network contributing to leprosy. For additional gene expression data of ovarian cancer, two candidate subnetworks, PI3K-AKT and Notch signaling pathways, were considered and identified respectively. CONCLUSIONS: The proposed method, accounting for the vertex changes and edge changes simultaneously, is valid and powerful to capture the group difference of biological networks.