This work discusses the consensus tracking for stochastic multi-agent systems with a leader-follower structure. An observer-based distributed control approach is put forward, leveraging control Lyapunov functions and quadratic programming framework. This control method ensures that each follower can track with the leader's state in the sense of expectation, even under stochastic disturbances. Two observers are given for each follower to observe its own state and the leader's state information, respectively, enabling fully distributed control requirement. Theoretical analysis guarantees the convergence of this control approach, and simulation results validate its effectiveness in achieving consensus tracking.

Traditional 3D garment creation is labor-intensive, involving sketching, modeling, UV mapping, and texturing, which are time-consuming and costly. Recent advances in diffusion-based generative models have enabled new possibilities for 3D garment generation from text prompts, images, and videos. However, existing methods either suffer from inconsistencies among multi-view images or require additional processes to separate cloth from the underlying human model. In this paper, we propose GarmentDreamer, a novel method that leverages 3D Gaussian Splatting (GS) as guidance to generate wearable, simulation-ready 3D garment meshes from text prompts. In contrast to using multi-view images directly predicted by generative models as guidance, our 3DGS guidance ensures consistent optimization in both garment deformation and texture synthesis. Our method introduces a novel garment augmentation module, guided by normal and RGBA information, and employs implicit Neural Texture Fields (NeTF) combined with Variational Score Distillation (VSD) to generate diverse geometric and texture details. We validate the effectiveness of our approach through comprehensive qualitative and quantitative experiments, showcasing the superior performance of GarmentDreamer over state-of-the-art alternatives11Demos and codes are available at https://xuan-li.github.io/GarmentDreamerDemo/.

Fitting a body to a 3D clothed human point cloud is a common yet challenging task. Traditional optimization-based approaches use multi-stage pipelines that are sensitive to pose initialization, while recent learning-based methods often struggle with generalization across diverse poses and garment types. We propose Equivariant Tightness Fitting for Clothed Humans, or ETCH, a novel pipeline that estimates cloth-to-body surface mapping through locally approximate SE(3) equivariance, encoding tightness as displacement vectors from the cloth surface to the underlying body. Following this mapping, pose-invariant body features regress sparse body markers, simplifying clothed human fitting into an inner-body marker fitting task. Extensive experiments on CAPE and 4D-Dress show that ETCH significantly outperforms state-of-the-art methods -- both tightness-agnostic and tightness-aware -- in body fitting accuracy on loose clothing (16.7% ~ 69.5%) and shape accuracy (average 49.9%). Our equivariant tightness design can even reduce directional errors by (67.2% ~ 89.8%) in one-shot (or out-of-distribution) settings (~ 1% data). Qualitative results demonstrate strong generalization of ETCH, regardless of challenging poses, unseen shapes, loose clothing, and non-rigid dynamics. We will release the code and models soon for research purposes at https://boqian-li.github.io/ETCH/.

Face aging has become a crucial task in computer vision, with applications ranging from entertainment to healthcare. However, existing methods struggle with achieving a realistic and seamless transformation across the entire lifespan, especially when handling large age gaps or extreme head poses. The core challenge lies in balancing $age\ accuracy$ and $identity\ preservation$—what we refer to as the $Age\text{-}ID\ trade\text{-}off$. Most prior methods either prioritize age transformation at the expense of identity consistency or vice versa. In this work, we address this issue by proposing a $two\text{-}pass$ face aging framework, named $Cradle2Cane$, based on few-step text-to-image (T2I) diffusion models. The first pass focuses on solving $age\ accuracy$ by introducing an adaptive noise injection ($AdaNI$) mechanism. This mechanism is guided by including prompt descriptions of age and gender for the given person as the textual condition. Also, by adjusting the noise level, we can control the strength of aging while allowing more flexibility in transforming the face. However, identity preservation is weakly ensured here to facilitate stronger age transformations. In the second pass, we enhance $identity\ preservation$ while maintaining age-specific features by conditioning the model on two identity-aware embeddings ($IDEmb$): $SVR\text{-}ArcFace$ and $Rotate\text{-}CLIP$. This pass allows for denoising the transformed image from the first pass, ensuring stronger identity preservation without compromising the aging accuracy. Both passes are $jointly\ trained\ in\ an\ end\text{-}to\text{-}end\ way\$. Extensive experiments on the CelebA-HQ test dataset, evaluated through Face++ and Qwen-VL protocols, show that our $Cradle2Cane$ outperforms existing face aging methods in age accuracy and identity consistency. Additionally, $Cradle2Cane$ demonstrates superior robustness when applied to in-the-wild human face images, where prior methods often fail. This significantly broadens its applicability to more diverse and unconstrained real-world scenarios. Code is available at https://github.com/byliutao/Cradle2Cane.

In the control problems of multi-agent systems, collision avoidance is a fundamental safety requirement. One effective approach to ensure safety involves combining control barrier functions (CBFs) with quadratic programming (QP), where nominal control inputs are incorporated into QPs to achieve desired control objectives. Additionally, it is crucial to study the control performance of multi-agent systems to balance these objectives with control efforts. This work demonstrates that the performance index is closely related to the hyperparameters in the CBF-based QP controller, and the Bayesian optimization algorithm is used to optimize and improve performance. Firstly, a safe control approach is developed and a unified performance enhancement framework is established to optimize the performance index. Hyperparameters are then explored and categorized, introducing the concept of feasible hyperparameters to describe the attainability of control objectives. Subsequently, the constrained Bayesian optimization algorithm is employed to identify a set of feasible and optimal hyperparameters in a data-driven manner, even when the functional expressions of performance and constraints are unknown. Finally, experiments are conducted to demonstrate the feasibility of the proposed methods in multi-agent systems. Note to Practitioners—Both safety and optimality are of great importance in the control systems. The design and development of controllers for multi-agent systems are currently undergoing significant evolution. Academic researchers and industrial practitioners are actively refining controller designs to perform better in a variety of collaborative tasks. With practical applications in mind, there is a growing demand for control techniques capable of ensuring a safe operating environment while maintaining efficiency in energy consumption. Therefore, this paper aims to furnish practitioners and researchers with a safe control framework, facilitating the refinement of optimal control solutions for efficient collaboration among multiple agents.

This article addresses the consensus tracking control of multiagent systems (MASs) via a quadratic programming (QP) optimization framework, where the control Lyapunov function (CLF) condition serves as a constraint. The optimal controllers, derived through the QP solver, not only ensure the tracking control objective but also minimize the cost functions of agents. To enhance energy efficiency, discontinuous control methods, such as intermittent control strategy and event-triggered mechanism, are employed in the control framework. The CLF-based QP controllers are only updated at specific time instants, in order to reduce the frequency of QP problem-solving. In addition to considering optimization, the proposed methods are extended to uncertain MASs to enhance robustness, where the uncertainty is modeled by Gaussian process regression. In the end, simulation results are provided to demonstrate the feasibility of the theoretical analysis.

The fully distributed consensus tracking of stochastic nonlinear multiagent systems (MASs) is investigated with Markovian switching topologies and intermittent control strategy, where the dynamics of agents are depicted by Itô differential equations and the leader’s information is just known for a fraction of followers. The switching mechanism of interaction topologies is modeled as a Markov process. A novel class of fully distributed control protocols is proposed via intermittent control method, which is only associated with the relative state measurements of neighbors and does not involve any global information. Meanwhile, the control gains are designed to be intermittently adaptive, which can effectively reduce energy consumption and avoid the gains being larger than those needed in practice. Several sufficient conditions and corresponding proofs are provided by using the Lyapunov stability theory. Finally, numerical simulation is presented to state the feasibility of the theoretical results.