Search

Recently, permissioned blockchain has been extensively explored in various fields, such as asset management, supply chain, healthcare, and many others. Many scholars are dedicated to improving its verifiability, scalability, and performance based on sharding techniques, including grouping nodes and handling cross-shard transactions. However, they ignore the node vulnerability problem, i.e., there is no guarantee that nodes will not be maliciously controlled throughout their life cycle. Facing this challenge, we propose RecAGT, a novel identification scheme aimed at reducing communication overhead and identifying potential malicious nodes. First, shard testable codes are designed to encode the original data in case of a leak of confidential data. Second, a new identity proof protocol is presented as evidence against malicious behavior. Finally, adaptive group testing is chosen to identify malicious nodes. Notably, our work focuses on the internal operation within the committee and can thus be applied to any sharding permissioned blockchains. Simulation results show that our proposed scheme can effectively identify malicious nodes with low communication and computational costs., Comment: Accepted by the 23rd International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP 2023)

We present a novel method for reconstructing clothed humans from a sparse set of, e.g., 1 to 6 RGB images. Despite impressive results from recent works employing deep implicit representation, we revisit the volumetric approach and demonstrate that better performance can be achieved with proper system design. The volumetric representation offers significant advantages in leveraging 3D spatial context through 3D convolutions, and the notorious quantization error is largely negligible with a reasonably large yet affordable volume resolution, e.g., 512. To handle memory and computation costs, we propose a sophisticated coarse-to-fine strategy with voxel culling and subspace sparse convolution. Our method starts with a discretized visual hull to compute a coarse shape and then focuses on a narrow band nearby the coarse shape for refinement. Once the shape is reconstructed, we adopt an image-based rendering approach, which computes the colors of surface points by blending input images with learned weights. Extensive experimental results show that our method significantly reduces the mean point-to-surface (P2S) precision of state-of-the-art methods by more than 50% to achieve approximately 2mm accuracy with a 512 volume resolution. Additionally, images rendered from our textured model achieve a higher peak signal-to-noise ratio (PSNR) compared to state-of-the-art methods.

Reconstructing neural radiance fields with explicit volumetric representations, demonstrated by Plenoxels, has shown remarkable advantages on training and rendering efficiency, while grid-based representations typically induce considerable overhead for storage and transmission. In this work, we present a simple and effective framework for pursuing compact radiance fields from the perspective of compression methodology. By exploiting intrinsic properties exhibiting in grid models, a non-uniform compression stem is developed to significantly reduce model complexity and a novel parameterized module, named Neural Codebook, is introduced for better encoding high-frequency details specific to per-scene models via a fast optimization. Our approach can achieve over 40 $\times$ reduction on grid model storage with competitive rendering quality. In addition, the method can achieve real-time rendering speed with 180 fps, realizing significant advantage on storage cost compared to real-time rendering methods., Comment: Accepted by ICME 2023

Image colorization is a challenging problem due to multi-modal uncertainty and high ill-posedness. Directly training a deep neural network usually leads to incorrect semantic colors and low color richness. While transformer-based methods can deliver better results, they often rely on manually designed priors, suffer from poor generalization ability, and introduce color bleeding effects. To address these issues, we propose DDColor, an end-to-end method with dual decoders for image colorization. Our approach includes a pixel decoder and a query-based color decoder. The former restores the spatial resolution of the image, while the latter utilizes rich visual features to refine color queries, thus avoiding hand-crafted priors. Our two decoders work together to establish correlations between color and multi-scale semantic representations via cross-attention, significantly alleviating the color bleeding effect. Additionally, a simple yet effective colorfulness loss is introduced to enhance the color richness. Extensive experiments demonstrate that DDColor achieves superior performance to existing state-of-the-art works both quantitatively and qualitatively. The codes and models are publicly available at https://github.com/piddnad/DDColor., Comment: ICCV 2023; Code: https://github.com/piddnad/DDColor

In this paper, we present a novel and effective framework, named 4K-NeRF, to pursue high fidelity view synthesis on the challenging scenarios of ultra high resolutions, building on the methodology of neural radiance fields (NeRF). The rendering procedure of NeRF-based methods typically relies on a pixel-wise manner in which rays (or pixels) are treated independently on both training and inference phases, limiting its representational ability on describing subtle details, especially when lifting to a extremely high resolution. We address the issue by exploring ray correlation to enhance high-frequency details recovery. Particularly, we use the 3D-aware encoder to model geometric information effectively in a lower resolution space and recover fine details through the 3D-aware decoder, conditioned on ray features and depths estimated by the encoder. Joint training with patch-based sampling further facilitates our method incorporating the supervision from perception oriented regularization beyond pixel-wise loss. Benefiting from the use of geometry-aware local context, our method can significantly boost rendering quality on high-frequency details compared with modern NeRF methods, and achieve the state-of-the-art visual quality on 4K ultra-high-resolution scenarios. Code Available at \url{https://github.com/frozoul/4K-NeRF}

Approximating radiance fields with volumetric grids is one of promising directions for improving NeRF, represented by methods like Plenoxels and DVGO, which achieve super-fast training convergence and real-time rendering. However, these methods typically require a tremendous storage overhead, costing up to hundreds of megabytes of disk space and runtime memory for a single scene. We address this issue in this paper by introducing a simple yet effective framework, called vector quantized radiance fields (VQRF), for compressing these volume-grid-based radiance fields. We first present a robust and adaptive metric for estimating redundancy in grid models and performing voxel pruning by better exploring intermediate outputs of volumetric rendering. A trainable vector quantization is further proposed to improve the compactness of grid models. In combination with an efficient joint tuning strategy and post-processing, our method can achieve a compression ratio of 100$\times$ by reducing the overall model size to 1 MB with negligible loss on visual quality. Extensive experiments demonstrate that the proposed framework is capable of achieving unrivaled performance and well generalization across multiple methods with distinct volumetric structures, facilitating the wide use of volumetric radiance fields methods in real-world applications. Code Available at \url{https://github.com/AlgoHunt/VQRF}

We present an explicit-grid based method for efficiently reconstructing streaming radiance fields for novel view synthesis of real world dynamic scenes. Instead of training a single model that combines all the frames, we formulate the dynamic modeling problem with an incremental learning paradigm in which per-frame model difference is trained to complement the adaption of a base model on the current frame. By exploiting the simple yet effective tuning strategy with narrow bands, the proposed method realizes a feasible framework for handling video sequences on-the-fly with high training efficiency. The storage overhead induced by using explicit grid representations can be significantly reduced through the use of model difference based compression. We also introduce an efficient strategy to further accelerate model optimization for each frame. Experiments on challenging video sequences demonstrate that our approach is capable of achieving a training speed of 15 seconds per-frame with competitive rendering quality, which attains $1000 \times$ speedup over the state-of-the-art implicit methods. Code is available at https://github.com/AlgoHunt/StreamRF., Comment: Accepted at NeurIPS 2022

The synthetic dimension opens new horizons in quantum physics and topological photonics by enabling new dimensions for field and particle manipulations. The most appealing property of the photonic synthetic dimension is its ability to emulate high-dimensional optical behavior in a unitary physical system. Here we show that the photonic synthetic dimension can transform technical problems in photonic systems between dimensionalities, providing unexpected solutions to technical problems that are otherwise challenging. Specifically, we propose and experimentally demonstrate a photonic Galton board (PGB) in the temporal synthetic dimension, in which the temporal high-speed challenge is converted into a spatial fiber-optic length matching problem, leading to the experimental generation of tera-sample-per-second arbitrary waveforms. Limited by the speed of the measurement equipment, waveforms with sampling rates of up to 341.53 GSa/s are recorded. Our proposed PGB operating in the temporal synthetic dimension breaks the speed limit in a physical system, bringing arbitrary waveform generation into the terahertz regime. The concept of dimension conversion offers possible solutions to various physical dimension-related problems, such as super-resolution imaging, high-resolution spectroscopy, time measurement, etc.

In recent years, edge computing (EC) has attracted great attention for its high-speed computing and low-latency characteristics. However, there are many challenges in the implementation of EC. Firstly, user's privacy has been raised as a major concern because the edge devices may be untrustworthy. In the case of Private Edge Computing (PEC), a user wants to compute a matrix multiplication between its local matrix and one of the matrices in a library, which has been redundantly stored in edge devices. When utilizing resources of edge devices, the privacy requires that each edge device cannot know which matrix stored on it is desired by the user for the multiplication. Secondly, edge devices usually have limited communication and storage resources, which makes it impossible for them to store all matrices in the library. In this paper, we consider the limited resources of edge devices and propose an unified framework for PEC. Within the framework, we study two highly-coupled problems, (1) storage allocation, that determines which matrices are stored on each edge device, and (2) computation design, that determines which matrices (or linear combinations of them) in each edge device are selected to participate in the computing process with the privacy consideration. Specifically, we give a general storage allocation scheme and then design two feasible private computation schemes, i.e., General Private Computation (GPC) scheme and Private Coded Computation (PCC) scheme. In particular, GPC can be applied in general case and PCC can only be applied in special cases, while PCC achieves less communication load. We theoretically analyze the proposed computing schemes and compare them with other schemes. Finally, we conduct extensive simulations to show the effectiveness of the proposed schemes.

In this work, we propose a novel two-stage framework, called FaceShifter, for high fidelity and occlusion aware face swapping. Unlike many existing face swapping works that leverage only limited information from the target image when synthesizing the swapped face, our framework, in its first stage, generates the swapped face in high-fidelity by exploiting and integrating the target attributes thoroughly and adaptively. We propose a novel attributes encoder for extracting multi-level target face attributes, and a new generator with carefully designed Adaptive Attentional Denormalization (AAD) layers to adaptively integrate the identity and the attributes for face synthesis. To address the challenging facial occlusions, we append a second stage consisting of a novel Heuristic Error Acknowledging Refinement Network (HEAR-Net). It is trained to recover anomaly regions in a self-supervised way without any manual annotations. Extensive experiments on wild faces demonstrate that our face swapping results are not only considerably more perceptually appealing, but also better identity preserving in comparison to other state-of-the-art methods., Comment: Accepted to CVPR 2020 (Oral), generated dataset and project webpage: lingzhili.com/FaceShifterPage/

In this paper we propose a novel image representation called face X-ray for detecting forgery in face images. The face X-ray of an input face image is a greyscale image that reveals whether the input image can be decomposed into the blending of two images from different sources. It does so by showing the blending boundary for a forged image and the absence of blending for a real image. We observe that most existing face manipulation methods share a common step: blending the altered face into an existing background image. For this reason, face X-ray provides an effective way for detecting forgery generated by most existing face manipulation algorithms. Face X-ray is general in the sense that it only assumes the existence of a blending step and does not rely on any knowledge of the artifacts associated with a specific face manipulation technique. Indeed, the algorithm for computing face X-ray can be trained without fake images generated by any of the state-of-the-art face manipulation methods. Extensive experiments show that face X-ray remains effective when applied to forgery generated by unseen face manipulation techniques, while most existing face forgery detection or deepfake detection algorithms experience a significant performance drop., Comment: Accepted to CVPR 2020 (Oral)

Implementation of a parity-time (PT) symmetric microwave photonic system in the optical wavelength space with spatial singularity is proposed. In the proposed PT-symmetric microwave photonic system, the gain and loss modes are confined in a single spatial resonator, which is different from a conventional PT-symmetric system in which the two modes are localized in two physically separated resonators to form one-dimensional spatial potential symmetry as required by the simplest one-dimensional parity transformation. We show that PT-symmetry can be implemented between subspaces in non-spatial parameter spaces, in which the gain and loss modes can perfectly overlay spatially but are distinguishable in the designated parameter space. The resultant spatial singularity enables the possibility in implementing PT-symmetric systems with increased structural simplicity, integration density and long-term stability. To prove the concept, a PT-symmetric optoelectronic oscillator (OEO) in the optical wavelength space is implemented. The OEO has a single-loop architecture, with the gain and loss microwave modes carried by two optical wavelengths to form two mutually coupled wavelength-space resonators (WSRs). PT-symmetry is achieved by controlling the wavelength spacing and the power contrast. The operation of PT symmetry in the OEO is verified by the generation of a 10-GHz microwave signal with a low phase noise of 129.3 dBc/Hz at 10-kHz offset frequency and a high sidemode suppression ratio (SMSR) of 66.22 dB. Compared with a conventional spatial PT-symmetric system, one in the wavelength space features a much simpler configuration, better stability and greater resilience to environmental interferences., Comment: 27 pages, 9 figures. Reported in Piers in June, 2019 in Rome; CIOP in August, 2019, in Xi'an and in MWP in October, 2019, in Ottawa