Search

In the field of high-dimensional data analysis, modeling methods based on quantile loss function are highly regarded due to their ability to provide a comprehensive statistical perspective and effective handling of heterogeneous data. In recent years, many studies have focused on using the parallel alternating direction method of multipliers (P-ADMM) to solve high-dimensional quantile regression and classification problems. One efficient strategy is to reformulate the quantile loss function by introducing slack variables. However, this reformulation introduces a theoretical challenge: even when the regularization term is convex, the convergence of the algorithm cannot be guaranteed. To address this challenge, this paper proposes the Gaussian Back-Substitution strategy, which requires only a simple and effective correction step that can be easily integrated into existing parallel algorithm frameworks, achieving a linear convergence rate. Furthermore, this paper extends the parallel algorithm to handle some novel quantile loss classification models. Numerical simulations demonstrate that the proposed modified P-ADMM algorithm exhibits excellent performance in terms of reliability and efficiency.

Effectively modeling the interaction between human hands and objects is challenging due to the complex physical constraints and the requirement for high generation efficiency in applications. Prior approaches often employ computationally intensive two-stage approaches, which first generate an intermediate representation, such as contact maps, followed by an iterative optimization procedure that updates hand meshes to capture the hand-object relation. However, due to the high computation complexity during the optimization stage, such strategies often suffer from low efficiency in inference. To address this limitation, this work introduces a novel diffusion-model-based approach that generates the grasping pose in a one-stage manner. This allows us to significantly improve generation speed and the diversity of generated hand poses. In particular, we develop a Latent Diffusion Model with an Adaptation Module for object-conditioned hand pose generation and a contact-aware loss to enforce the physical constraints between hands and objects. Extensive experiments demonstrate that our method achieves faster inference, higher diversity, and superior pose quality than state-of-the-art approaches. Code is available at \href{https://github.com/wuxiaofei01/FastGrasp}{https://github.com/wuxiaofei01/FastGrasp.}

We present a novel approach for synthesizing 3D talking heads with controllable emotion, featuring enhanced lip synchronization and rendering quality. Despite significant progress in the field, prior methods still suffer from multi-view consistency and a lack of emotional expressiveness. To address these issues, we collect EmoTalk3D dataset with calibrated multi-view videos, emotional annotations, and per-frame 3D geometry. By training on the EmoTalk3D dataset, we propose a \textit{`Speech-to-Geometry-to-Appearance'} mapping framework that first predicts faithful 3D geometry sequence from the audio features, then the appearance of a 3D talking head represented by 4D Gaussians is synthesized from the predicted geometry. The appearance is further disentangled into canonical and dynamic Gaussians, learned from multi-view videos, and fused to render free-view talking head animation. Moreover, our model enables controllable emotion in the generated talking heads and can be rendered in wide-range views. Our method exhibits improved rendering quality and stability in lip motion generation while capturing dynamic facial details such as wrinkles and subtle expressions. Experiments demonstrate the effectiveness of our approach in generating high-fidelity and emotion-controllable 3D talking heads. The code and EmoTalk3D dataset are released at https://nju-3dv.github.io/projects/EmoTalk3D., Comment: ECCV 2024

Distributed model fitting refers to the process of fitting a mathematical or statistical model to the data using distributed computing resources, such that computing tasks are divided among multiple interconnected computers or nodes, often organized in a cluster or network. Most of the existing methods for distributed model fitting are to formulate it in a consensus optimization problem, and then build up algorithms based on the alternating direction method of multipliers (ADMM). This paper introduces a novel parallel framework for achieving a distributed model fitting. In contrast to previous consensus frameworks, the introduced parallel framework offers two notable advantages. Firstly, it exhibits insensitivity to sample partitioning, meaning that the solution of the algorithm remains unaffected by variations in the number of slave nodes or/and the amount of data each node carries. Secondly, fewer variables are required to be updated at each iteration, so that the proposed parallel framework performs in a more succinct and efficient way, and adapts to high-dimensional data. In addition, we prove that the algorithms under the new parallel framework have a worst-case linear convergence rate in theory. Numerical experiments confirm the generality, robustness, and accuracy of our proposed parallel framework.

3D Gaussian Splatting showcases notable advancements in photo-realistic and real-time novel view synthesis. However, it faces challenges in modeling mirror reflections, which exhibit substantial appearance variations from different viewpoints. To tackle this problem, we present MirrorGaussian, the first method for mirror scene reconstruction with real-time rendering based on 3D Gaussian Splatting. The key insight is grounded on the mirror symmetry between the real-world space and the virtual mirror space. We introduce an intuitive dual-rendering strategy that enables differentiable rasterization of both the real-world 3D Gaussians and the mirrored counterpart obtained by reflecting the former about the mirror plane. All 3D Gaussians are jointly optimized with the mirror plane in an end-to-end framework. MirrorGaussian achieves high-quality and real-time rendering in scenes with mirrors, empowering scene editing like adding new mirrors and objects. Comprehensive experiments on multiple datasets demonstrate that our approach significantly outperforms existing methods, achieving state-of-the-art results. Project page: https://mirror-gaussian.github.io/.

Co-speech gestures, if presented in the lively form of videos, can achieve superior visual effects in human-machine interaction. While previous works mostly generate structural human skeletons, resulting in the omission of appearance information, we focus on the direct generation of audio-driven co-speech gesture videos in this work. There are two main challenges: 1) A suitable motion feature is needed to describe complex human movements with crucial appearance information. 2) Gestures and speech exhibit inherent dependencies and should be temporally aligned even of arbitrary length. To solve these problems, we present a novel motion-decoupled framework to generate co-speech gesture videos. Specifically, we first introduce a well-designed nonlinear TPS transformation to obtain latent motion features preserving essential appearance information. Then a transformer-based diffusion model is proposed to learn the temporal correlation between gestures and speech, and performs generation in the latent motion space, followed by an optimal motion selection module to produce long-term coherent and consistent gesture videos. For better visual perception, we further design a refinement network focusing on missing details of certain areas. Extensive experimental results show that our proposed framework significantly outperforms existing approaches in both motion and video-related evaluations. Our code, demos, and more resources are available at https://github.com/thuhcsi/S2G-MDDiffusion., Comment: 22 pages, 8 figures, CVPR 2024

Existing NeRF-based methods for large scene reconstruction often have limitations in visual quality and rendering speed. While the recent 3D Gaussian Splatting works well on small-scale and object-centric scenes, scaling it up to large scenes poses challenges due to limited video memory, long optimization time, and noticeable appearance variations. To address these challenges, we present VastGaussian, the first method for high-quality reconstruction and real-time rendering on large scenes based on 3D Gaussian Splatting. We propose a progressive partitioning strategy to divide a large scene into multiple cells, where the training cameras and point cloud are properly distributed with an airspace-aware visibility criterion. These cells are merged into a complete scene after parallel optimization. We also introduce decoupled appearance modeling into the optimization process to reduce appearance variations in the rendered images. Our approach outperforms existing NeRF-based methods and achieves state-of-the-art results on multiple large scene datasets, enabling fast optimization and high-fidelity real-time rendering., Comment: Accepted to CVPR 2024. Project website: https://vastgaussian.github.io

In this paper, we introduce RealDex, a pioneering dataset capturing authentic dexterous hand grasping motions infused with human behavioral patterns, enriched by multi-view and multimodal visual data. Utilizing a teleoperation system, we seamlessly synchronize human-robot hand poses in real time. This collection of human-like motions is crucial for training dexterous hands to mimic human movements more naturally and precisely. RealDex holds immense promise in advancing humanoid robot for automated perception, cognition, and manipulation in real-world scenarios. Moreover, we introduce a cutting-edge dexterous grasping motion generation framework, which aligns with human experience and enhances real-world applicability through effectively utilizing Multimodal Large Language Models. Extensive experiments have demonstrated the superior performance of our method on RealDex and other open datasets. The complete dataset and code will be made available upon the publication of this work., Comment: Project Page: https://4dvlab.github.io/RealDex_page/

As the latest advancements in natural language processing, large language models (LLMs) have achieved human-level language understanding and generation abilities in many real-world tasks, and even have been regarded as a potential path to the artificial general intelligence. To better facilitate research on LLMs, many open-source LLMs, such as Llama 2 and Falcon, have recently been proposed and gained comparable performances to proprietary models. However, these models are primarily designed for English scenarios and exhibit poor performances in Chinese contexts. In this technical report, we propose YAYI 2, including both base and chat models, with 30 billion parameters. YAYI 2 is pre-trained from scratch on a multilingual corpus which contains 2.65 trillion tokens filtered by our pre-training data processing pipeline. The base model is aligned with human values through supervised fine-tuning with millions of instructions and reinforcement learning from human feedback. Extensive experiments on multiple benchmarks, such as MMLU and CMMLU, consistently demonstrate that the proposed YAYI 2 outperforms other similar sized open-source models.

Capturing and preserving motion semantics is essential to motion retargeting between animation characters. However, most of the previous works neglect the semantic information or rely on human-designed joint-level representations. Here, we present a novel Semantics-aware Motion reTargeting (SMT) method with the advantage of vision-language models to extract and maintain meaningful motion semantics. We utilize a differentiable module to render 3D motions. Then the high-level motion semantics are incorporated into the motion retargeting process by feeding the vision-language model with the rendered images and aligning the extracted semantic embeddings. To ensure the preservation of fine-grained motion details and high-level semantics, we adopt a two-stage pipeline consisting of skeleton-aware pre-training and fine-tuning with semantics and geometry constraints. Experimental results show the effectiveness of the proposed method in producing high-quality motion retargeting results while accurately preserving motion semantics., Comment: Accepted in CVPR2024

The parallel alternating direction method of multipliers (ADMM) algorithm is widely recognized for its effectiveness in handling large-scale datasets stored in a distributed manner, making it a popular choice for solving statistical learning models. However, there is currently limited research on parallel algorithms specifically designed for high-dimensional regression with combined (composite) regularization terms. These terms, such as elastic-net, sparse group lasso, sparse fused lasso, and their nonconvex variants, have gained significant attention in various fields due to their ability to incorporate prior information and promote sparsity within specific groups or fused variables. The scarcity of parallel algorithms for combined regularizations can be attributed to the inherent nonsmoothness and complexity of these terms, as well as the absence of closed-form solutions for certain proximal operators associated with them. In this paper, we propose a unified constrained optimization formulation based on the consensus problem for these types of convex and nonconvex regression problems and derive the corresponding parallel ADMM algorithms. Furthermore, we prove that the proposed algorithm not only has global convergence but also exhibits linear convergence rate. Extensive simulation experiments, along with a financial example, serve to demonstrate the reliability, stability, and scalability of our algorithm. The R package for implementing the proposed algorithms can be obtained at https://github.com/xfwu1016/CPADMM.

In many statistical modeling problems, such as classification and regression, it is common to encounter sparse and blocky coefficients. Sparse fused Lasso is specifically designed to recover these sparse and blocky structured features, especially in cases where the design matrix has ultrahigh dimensions, meaning that the number of features significantly surpasses the number of samples. Quantile loss is a well-known robust loss function that is widely used in statistical modeling. In this paper, we propose a new sparse fused lasso classification model, and develop a unified multi-block linearized alternating direction method of multipliers algorithm that effectively selects sparse and blocky features for regression and classification. Our algorithm has been proven to converge with a derived linear convergence rate. Additionally, our algorithm has a significant advantage over existing methods for solving ultrahigh dimensional sparse fused Lasso regression and classification models due to its lower time complexity. Note that the algorithm can be easily extended to solve various existing fused Lasso models. Finally, we present numerical results for several synthetic and real-world examples, which demonstrate the robustness, scalability, and accuracy of the proposed classification model and algorithm

The automatic co-speech gesture generation draws much attention in computer animation. Previous works designed network structures on individual datasets, which resulted in a lack of data volume and generalizability across different motion capture standards. In addition, it is a challenging task due to the weak correlation between speech and gestures. To address these problems, we present UnifiedGesture, a novel diffusion model-based speech-driven gesture synthesis approach, trained on multiple gesture datasets with different skeletons. Specifically, we first present a retargeting network to learn latent homeomorphic graphs for different motion capture standards, unifying the representations of various gestures while extending the dataset. We then capture the correlation between speech and gestures based on a diffusion model architecture using cross-local attention and self-attention to generate better speech-matched and realistic gestures. To further align speech and gesture and increase diversity, we incorporate reinforcement learning on the discrete gesture units with a learned reward function. Extensive experiments show that UnifiedGesture outperforms recent approaches on speech-driven gesture generation in terms of CCA, FGD, and human-likeness. All code, pre-trained models, databases, and demos are available to the public at https://github.com/YoungSeng/UnifiedGesture., Comment: 16 pages, 11 figures, ACM MM 2023

The parallel alternating direction method of multipliers (ADMM) algorithms have gained popularity in statistics and machine learning due to their efficient handling of large sample data problems. However, the parallel structure of these algorithms, based on the consensus problem, can lead to an excessive number of auxiliary variables when applied to highdimensional data, resulting in large computational burden. In this paper, we propose a partition-insensitive parallel framework based on the linearized ADMM (LADMM) algorithm and apply it to solve nonconvex penalized high-dimensional regression problems. Compared to existing parallel ADMM algorithms, our algorithm does not rely on the consensus problem, resulting in a significant reduction in the number of variables that need to be updated at each iteration. It is worth noting that the solution of our algorithm remains largely unchanged regardless of how the total sample is divided, which is known as partition-insensitivity. Furthermore, under some mild assumptions, we prove the convergence of the iterative sequence generated by our parallel algorithm. Numerical experiments on synthetic and real datasets demonstrate the feasibility and validity of the proposed algorithm. We provide a publicly available R software package to facilitate the implementation of the proposed algorithm.

In this paper, we introduce the DiffuseStyleGesture+, our solution for the Generation and Evaluation of Non-verbal Behavior for Embodied Agents (GENEA) Challenge 2023, which aims to foster the development of realistic, automated systems for generating conversational gestures. Participants are provided with a pre-processed dataset and their systems are evaluated through crowdsourced scoring. Our proposed model, DiffuseStyleGesture+, leverages a diffusion model to generate gestures automatically. It incorporates a variety of modalities, including audio, text, speaker ID, and seed gestures. These diverse modalities are mapped to a hidden space and processed by a modified diffusion model to produce the corresponding gesture for a given speech input. Upon evaluation, the DiffuseStyleGesture+ demonstrated performance on par with the top-tier models in the challenge, showing no significant differences with those models in human-likeness, appropriateness for the interlocutor, and achieving competitive performance with the best model on appropriateness for agent speech. This indicates that our model is competitive and effective in generating realistic and appropriate gestures for given speech. The code, pre-trained models, and demos are available at https://github.com/YoungSeng/DiffuseStyleGesture/tree/DiffuseStyleGesturePlus/BEAT-TWH-main., Comment: 7 pages, 8 figures, ICMI 2023

Plasmonic enhancement of nonlinear light-matter interaction can be achieved via dedicated optimization of resonant plasmonic modes that are spectrally matched to the different wavelengths involved in the particular nonlinear optical process. In this work, we investigate the generation and enhancement of broadband four-wave mixing (FWM) in a plasmonic azimuthally chirped grating (ACG). The azimuthally varying grating periodicity in an ACG offers a well-defined channel to mediate the near field and the far field over a broad range of wavelengths. However, the particular mechanism responsible for field enhancement in such a platform depends on the interplay between the effects manifested by both the groove geometry and the grating's periodicity. This work delineates the collective contribution of groove geometry-dependent localized surface plasmon resonance (LSPR) and periodicity-dependent plasmonic surface lattice resonance (PSLR) over a broad range of wavelengths to bring into effect the enhancement of broadband FWM in an ACG.

The deployment of plasmonic nanostructures to enhance nonlinear signal generation requires effective far-to-near field coupling and phase matching for frequency conversion. While the latter can be easily achieved at plasmonic hotspots, the former is an antenna problem that requires dedicated structural design and optimization. Plasmonic gratings are a simple but effective platform for nonlinear signal generation since they provide a well-defined momentum for photon-plasmon coupling and local hotspots for frequency conversion. In this work, a plasmonic azimuthally chirped grating (ACG), which provides spatially resolved broadband momentum for photon-plasmon coupling, was exploited to investigate the plasmonic enhancement effect in two nonlinear optical processes, namely two-photon photoluminescence (TPPL) and second-harmonic generation (SHG). The spatial distributions of the nonlinear signals were determined experimentally by hyperspectral mapping with ultrashort pulsed excitation. The experimental spatial distributions of nonlinear signals agree very well with the analytical prediction based solely on photon-plasmon coupling with the momentum of the ACG, revealing the antenna function of the grating in plasmonic nonlinear signal generation. This work highlights the importance of the antenna effect of the gratings for nonlinear signal generation and provides insight into the enhancement mechanism of plasmonic gratings in addition to local hotspot engineering., Comment: 6 pages, 3 figures