Synthetic aperture radar (SAR) is an effective imaging and observation sensor that has been widely applied in both military and civilian fields. Deep learning approaches have gained prominence in SAR target recognition and received extensive attention. However, these methods often struggle when data is scarce, leading to insufficient training and challenges in effective feature extraction. To address this limitation, we propose a less data-dependent feature extraction framework. Specifically, we introduce the dual-tree complex wavelet transform (DTCWT) to capture multi-frequency feature details of SAR images, integrated with convolutional neural network. This approach enables effective extraction of high- and low-frequency information. By leveraging the characteristics of these frequency features, low-frequency subbands are used to emphasize the global structural features in the images, and high-frequency subbands are employed to identify the significance of different regions in the images. In response to the aforementioned characteristics, we introduced an attention mechanism to effectively incorporate high-frequency local information into low-frequency global information, thereby enhancing feature representation and recognition efficiency. Moreover, we propose an adaptive rotational convolution, and apply it to the high-frequency feature extraction. The adaptive rotational convolution can adapt to the directionally selective subbands with a single convolution kernel. Experiments conducted on the MSTAR and SAR car datasets demonstrate that the proposed method can achieve better recognition performance with fewer parameters, especially on small-scale datasets. The ablation study also confirms the effectiveness of the introduced DTCWT and rotational convolution.

BFT consensus that uses Trusted Execution Environments (TEEs) to improve the system tolerance and performance is gaining popularity. However, existing works suffer from TEE rollback issues, resulting in a tolerance-performance tradeoff. In this paper, we propose Achilles, an efficient TEE-assisted BFT protocol that breaks the tradeoff. The key idea behind Achilles is removing the expensive rollback prevention of TEEs from the critical path of committing transactions. To this end, Achilles adopts a rollback resilient recovery mechanism, which allows nodes to assist each other in recovering their states. Besides, Achilles follows the chaining spirit in modern chained BFT protocols and leverages customized chained commit rules to achieve linear message complexity, end-to-end transaction latency of four communication steps, and fault tolerance for the minority of Byzantine nodes. Achilles is the first TEE-assisted BFT protocol in line with CFT protocols in these metrics. We implement a prototype of Achilles based on Intel SGX and evaluate it in both LAN and WAN, showcasing its outperforming performance compared to several state-of-the-art counterparts.

Generating sewing patterns in garment design is receiving increasing attention due to its CG-friendly and flexible-editing nature. Previous sewing pattern generation methods have been able to produce exquisite clothing, but struggle to design complex garments with detailed control. To address these issues, we propose SewingLDM, a multi-modal generative model that generates sewing patterns controlled by text prompts, body shapes, and garment sketches. Initially, we extend the original vector of sewing patterns into a more comprehensive representation to cover more intricate details and then compress them into a compact latent space. To learn the sewing pattern distribution in the latent space, we design a two-step training strategy to inject the multi-modal conditions, \ie, body shapes, text prompts, and garment sketches, into a diffusion model, ensuring the generated garments are body-suited and detail-controlled. Comprehensive qualitative and quantitative experiments show the effectiveness of our proposed method, significantly surpassing previous approaches in terms of complex garment design and various body adaptability. Our project page: https://shengqiliu1.github.io/SewingLDM.

3D face editing is a significant task in multimedia, aimed at the manipulation of 3D face models across various control signals. The success of 3D-aware GAN provides expressive 3D models learned from 2D single-view images only, encouraging researchers to discover semantic editing directions in its latent space. However, previous methods face challenges in balancing quality, efficiency, and generalization. To solve the problem, we explore the possibility of introducing the strength of diffusion model into 3D-aware GANs. In this paper, we presentFace Clan, a fast and text-general approach for generating and manipulating 3D faces based on arbitrary attribute descriptions. To achieve disentangled editing, we propose to diffuse on the latent space under a pair of opposite prompts to estimate the mask indicating the region of interest on latent codes. Based on the mask, we then apply denoising to the masked latent codes to reveal the editing direction. Our method offers a precisely controllable manipulation method, allowing users to intuitively customize regions of interest with the text description. Experiments demonstrate the effectiveness and generalization of our Face Clan for various pre-trained GANs. It offers an intuitive and wide application for text-guided face editing that contributes to the landscape of multimedia content creation. Our project page:https://windlikestone.github.io/Face_clan_website/.

Byzantine consensus is a fundamental building block in distributed cryptographic problems. Despite decades of research, most existing asynchronous consensus protocols require a strong trusted setup and expensive public-key cryptography. In this paper, we study asynchronous Byzantine consensus protocols that do not rely on a trusted setup and do not use public-key cryptography such as digital signatures. We give an Asynchronous Common Subset (ACS) protocol whose security is only based on cryptographic hash functions modeled as a random oracle. Our protocol has O(κn3) total communication and runs in expected O(1) rounds. The fact that we use only cryptographic hash functions also means that our protocol is post-quantum secure. The minimal use of cryptography and the small number of rounds make our protocol practical. We implement our protocol and evaluate it in a geo-distributed setting with up to 128 machines. Our experimental evaluation shows that our protocol is more efficient than the only other setup-free consensus protocol that has been implemented to date. En route to our asynchronous consensus protocols, we also introduce new primitives called asynchronous secret key sharing and cover gather, which may be of independent interest.

Deep learning methods have made profound advancements in the field of synthetic aperture radar (SAR) target recognition. Typically, a significant amount of training data is required. However, due to the high degree of prior expert knowledge required for the annotation of SAR images, it is challenging to obtain a large amount of labeled data, which significantly impacts the performance of target recognition. To address this issue, this paper introduces an Azimuth-Aware Multi-Head Residual Self-Attention Network (MHRA-Net) that can extract high discriminative features of targets. Initially, this model employs a sub-aperture decomposition method to expand target information across multiple azimuth angles. Subsequently, we design a multi-head residual self-attention mechanism that can extract salient features of targets from multiple perspectives. Finally, a multi-scale feature fusion module is used to extract both global and local information about the target, enhancing model robustness and allowing the network to achieve satisfactory recognition performance even under sample-constrained conditions. Experimental results on a 10-class vehicle SAR image dataset demonstrate the effectiveness of the proposed approach.

Abstract Texture editing is a crucial task in 3D modelling that allows users to automatically manipulate the surface materials of 3D models. However, the inherent complexity of 3D models and the ambiguous text description lead to the challenge of this task. To tackle this challenge, we propose ITEM3D, a Texture Editing Model designed for automatic 3D object editing according to the text Instructions. Leveraging the diffusion models and the differentiable rendering, ITEM3D takes the rendered images as the bridge between text and 3D representation and further optimizes the disentangled texture and environment map. Previous methods adopted the absolute editing direction, namely score distillation sampling (SDS) as the optimization objective, which unfortunately results in noisy appearances and text inconsistencies. To solve the problem caused by the ambiguous text, we introduce a relative editing direction, an optimization objective defined by the noise difference between the source and target texts, to release the semantic ambiguity between the texts and images. Additionally, we gradually adjust the direction during optimization to further address the unexpected deviation in the texture domain. Qualitative and quantitative experiments show that our ITEM3D outperforms the state‐of‐the‐art methods on various 3D objects. We also perform text‐guided relighting to show explicit control over lighting. Our project page: https://shengqiliu1.github.io/ITEM3D/ .

Synthesizing high-fidelity head avatars is a central problem for computer vision and graphics. While head avatar synthesis algorithms have advanced rapidly, the best ones still face great obstacles in real-world scenarios. One of the vital causes is the inadequate datasets -- 1) current public datasets can only support researchers to explore high-fidelity head avatars in one or two task directions; 2) these datasets usually contain digital head assets with limited data volume, and narrow distribution over different attributes, such as expressions, ages, and accessories. In this paper, we present RenderMe-360, a comprehensive 4D human head dataset to drive advance in head avatar algorithms across different scenarios. It contains massive data assets, with 243+ million complete head frames and over 800k video sequences from 500 different identities captured by multi-view cameras at 30 FPS. It is a large-scale digital library for head avatars with three key attributes: 1) High Fidelity: all subjects are captured in 360 degrees via 60 synchronized, high-resolution 2K cameras. 2) High Diversity: The collected subjects vary from different ages, eras, ethnicities, and cultures, providing abundant materials with distinctive styles in appearance and geometry. Moreover, each subject is asked to perform various dynamic motions, such as expressions and head rotations, which further extend the richness of assets. 3) Rich Annotations: the dataset provides annotations with different granularities: cameras' parameters, background matting, scan, 2D/3D facial landmarks, FLAME fitting, and text description. Based on the dataset, we build a comprehensive benchmark for head avatar research, with 16 state-of-the-art methods performed on five main tasks: novel view synthesis, novel expression synthesis, hair rendering, hair editing, and talking head generation. Our experiments uncover the strengths and flaws of state-of-the-art methods. RenderMe-360 opens the door for future exploration in modern head avatars. All of the data, code, and models will be publicly available at https://renderme-360.github.io/.

While implicit representations have achieved high-fidelity results in 3D rendering, it remains challenging to deforming and animating the implicit field. Existing works typically leverage data-dependent models as deformation priors, such as SMPL for human body animation. However, this dependency on category-specific priors limits them to generalize to other objects. To solve this problem, we propose a novel framework for deforming and animating the neural radiance field learned on \textit{arbitrary} objects. The key insight is that we introduce a cage-based representation as deformation prior, which is category-agnostic. Specifically, the deformation is performed based on an enclosing polygon mesh with sparsely defined vertices called \textit{cage} inside the rendering space, where each point is projected into a novel position based on the barycentric interpolation of the deformed cage vertices. In this way, we transform the cage into a generalized constraint, which is able to deform and animate arbitrary target objects while preserving geometry details. Based on extensive experiments, we demonstrate the effectiveness of our framework in the task of geometry editing, object animation and deformation transfer.