While network coverage maps continue to expand, many devices located in remote areas remain unconnected to terrestrial communication infrastructures, preventing them from getting access to the associated data-driven services. In this paper, we propose a ground-to-satellite cooperative federated learning (FL) methodology to facilitate machine learning service management over remote regions. Our methodology orchestrates satellite constellations to provide the following key functions during FL: (i) processing data offloaded from ground devices, (ii) aggregating models within device clusters, and (iii) relaying models/data to other satellites via inter-satellite links (ISLs). Due to the limited coverage time of each satellite over a particular remote area, we facilitate satellite transmission of trained models and acquired data to neighboring satellites via ISL, so that the incoming satellite can continue conducting FL for the region. We theoretically analyze the convergence behavior of our algorithm, and develop a training latency minimizer which optimizes over satellite-specific network resources, including the amount of data to be offloaded from ground devices to satellites and satellites' computation speeds. Through experiments on three datasets, we show that our methodology can significantly speed up the convergence of FL compared with terrestrial-only and other satellite baseline approaches.
Reconstructing the human body from single-view videos plays a pivotal role in the virtual reality domain. One prevalent application scenario necessitates the rapid reconstruction of high-fidelity 3D digital humans while simultaneously ensuring real-time rendering and interaction. Existing methods often struggle to fulfill both requirements. In this paper, we introduce Human101, a novel framework adept at producing high-fidelity dynamic 3D human reconstructions from 1-view videos by training 3D Gaussians in 100 seconds and rendering in 100+ FPS. Our method leverages the strengths of 3D Gaussian Splatting, which provides an explicit and efficient representation of 3D humans. Standing apart from prior NeRF-based pipelines, Human101 ingeniously applies a Human-centric Forward Gaussian Animation method to deform the parameters of 3D Gaussians, thereby enhancing rendering speed (i.e., rendering 1024-resolution images at an impressive 60+ FPS and rendering 512-resolution images at 100+ FPS). Experimental results indicate that our approach substantially eclipses current methods, clocking up to a 10 times surge in frames per second and delivering comparable or superior rendering quality. Code and demos will be released at https://github.com/longxiang-ai/Human101.
Private computation of nonlinear functions, such as Rectified Linear Units (ReLUs) and max-pooling operations, in deep neural networks (DNNs) poses significant challenges in terms of storage, bandwidth, and time consumption. To address these challenges, there has been a growing interest in utilizing privacy-preserving techniques that leverage polynomial activation functions and kernelized convolutions as alternatives to traditional ReLUs. However, these alternative approaches often suffer from a trade-off between achieving faster private inference (PI) and sacrificing model accuracy. In particular, when applied to much deeper networks, these methods encounter training instabilities, leading to issues like exploding gradients (resulting in NaNs) or suboptimal approximations. In this study, we focus on PolyKervNets, a technique known for offering improved dynamic approximations in smaller networks but still facing instabilities in larger and more complex networks. Our primary objective is to empirically explore optimization-based training recipes to enhance the performance of PolyKervNets in larger networks. By doing so, we aim to potentially eliminate the need for traditional nonlinear activation functions, thereby advancing the state-of-the-art in privacy-preserving deep neural network architectures. Code can be found on GitHub at: \url{https://github.com/tolusophy/PolyKervNets/}
With the widespread use of NeRF-based implicit 3D representation, the need for camera localization in the same representation becomes manifestly apparent. Doing so not only simplifies the localization process -- by avoiding an outside-the-NeRF-based localization -- but also has the potential to offer the benefit of enhanced localization. This paper studies the problem of localizing cameras in NeRF using a diffusion model for camera pose adjustment. More specifically, given a pre-trained NeRF model, we train a diffusion model that iteratively updates randomly initialized camera poses, conditioned upon the image to be localized. At test time, a new camera is localized in two steps: first, coarse localization using the proposed pose diffusion process, followed by local refinement steps of a pose inversion process in NeRF. In fact, the proposed camera localization by pose diffusion (CaLDiff) method also integrates the pose inversion steps within the diffusion process. Such integration offers significantly better localization, thanks to our downstream refinement-aware diffusion process. Our exhaustive experiments on challenging real-world data validate our method by providing significantly better results than the compared methods and the established baselines. Our source code will be made publicly available.
Variable curvature modeling tools provide an accurate means of controlling infinite degrees-of-freedom deformable bodies and structures. However, their forward and inverse Newton-Euler dynamics are fraught with high computational costs. Assuming piecewise constant strains across discretized Cosserat rods imposed on the soft material, a composite two time-scale singularly perturbed nonlinear backstepping control scheme is here introduced. This is to alleviate the long computational times of the recursive Newton-Euler dynamics for soft structures. Our contribution is three-pronged: (i) we decompose the system's Newton-Euler dynamics to a two coupled sub-dynamics by introducing a perturbation parameter; (ii) we then prescribe a set of stabilizing controllers for regulating each subsystem's dynamics; and (iii) we study the interconnected singularly perturbed system and analyze its stability.
Social recommendations have been widely adopted in substantial domains. Recently, graph neural networks (GNN) have been employed in recommender systems due to their success in graph representation learning. However, dealing with the dynamic property of social network data is a challenge. This research presents a novel method that provides social recommendations by incorporating the dynamic property of social network data in a heterogeneous graph. The model aims to capture user preference over time without going through the complexities of a dynamic graph by adding period nodes to define users' long-term and short-term preferences and aggregating assigned edge weights. The model is applied to real-world data to argue its superior performance. Promising results demonstrate the effectiveness of this model.
Pitch variability in rap vocals is overlooked in favor of the genre's uniquely dynamic rhythmic properties. We present an analysis of fundamental frequency (F0) variation in rap vocals over the past 14 years, focusing on song examples that represent the state of modern rap music. Our analysis aims at identifying meaningful trends over time, and is in turn a continuation of the 2023 analysis by Georgieva, Ripolles & McFee. They found rap to be an outlier with larger F0 variation compared to other genres, but with a declining trend since the genre's inception. However, they only analyzed data through 2010. Our analysis looks beyond 2010. We once again observe rap's large F0 variation, but with a decelerated decline in recent years.
Recently multi-armed bandit problem arises in many real-life scenarios where arms must be sampled in batches, due to limited time the agent can wait for the feedback. Such applications include biological experimentation and online marketing. The problem is further complicated when the number of arms is large and the number of batches is small. We consider pure exploration in a batched multi-armed bandit problem. We introduce a general linear programming framework that can incorporate objectives of different theoretical settings in best arm identification. The linear program leads to a two-stage algorithm that can achieve good theoretical properties. We demonstrate by numerical studies that the algorithm also has good performance compared to certain UCB-type or Thompson sampling methods.
Novel view synthesis has shown rapid progress recently, with methods capable of producing evermore photo-realistic results. 3D Gaussian Splatting has emerged as a particularly promising method, producing high-quality renderings of static scenes and enabling interactive viewing at real-time frame rates. However, it is currently limited to static scenes only. In this work, we extend 3D Gaussian Splatting to reconstruct dynamic scenes. We model the dynamics of a scene using a tunable MLP, which learns the deformation field from a canonical space to a set of 3D Gaussians per frame. To disentangle the static and dynamic parts of the scene, we learn a tuneable parameter for each Gaussian, which weighs the respective MLP parameters to focus attention on the dynamic parts. This improves the model's ability to capture dynamics in scenes with an imbalance of static to dynamic regions. To handle scenes of arbitrary length whilst maintaining high rendering quality, we introduce an adaptive window sampling strategy to partition the sequence into windows based on the amount of movement in the sequence. We train a separate dynamic Gaussian Splatting model for each window, allowing the canonical representation to change, thus enabling the reconstruction of scenes with significant geometric or topological changes. Temporal consistency is enforced using a fine-tuning step with self-supervising consistency loss on randomly sampled novel views. As a result, our method produces high-quality renderings of general dynamic scenes with competitive quantitative performance, which can be viewed in real-time with our dynamic interactive viewer.
Soft sensors are crucial in bridging autonomous systems' physical and digital realms, enhancing sensor fusion and perception. Instead of deploying soft sensors on the Cloud, this study shift towards employing on-device soft sensors, promising heightened efficiency and bolstering data security. Our approach substantially improves energy efficiency by deploying Artificial Intelligence (AI) directly on devices within a wireless sensor network. Furthermore, the synergistic integration of the Microcontroller Unit and Field-Programmable Gate Array (FPGA) leverages the rapid AI inference capabilities of the latter. Empirical evidence from our real-world use case demonstrates that FPGA-based soft sensors achieve inference times ranging remarkably from 1.04 to 12.04 microseconds. These compelling results highlight the considerable potential of our innovative approach for executing real-time inference tasks efficiently, thereby presenting a feasible alternative that effectively addresses the latency challenges intrinsic to Cloud-based deployments.