ease-preserving transfer

This work addresses the longstanding challenge in traditional garment design where ease—the intentional looseness of clothing relative to the body—cannot be explicitly controlled, edited, or transferred as an independent variable, often relying instead on geometric modeling or physical simulation with limited direct manipulability. The authors propose a novel representation that embeds garment meshes into a parametric human body model, explicitly encoding local ease through a spatially varying anisotropic triangle scaling field. This field serves as the core design variable and is integrated with user-defined pattern pieces and geometric-stitching constraints to optimize seam patterns. The method enables, for the first time, localized and explicit control over ease, supporting direct editing, intent-preserving transfer across body shapes, and pose-driven redistribution. Experiments demonstrate high fidelity in ease preservation, significant reduction of excessive stretching in target poses, and accurate transfer to novel body types. The system is publicly released.

This work addresses the challenge of preserving mapping continuity and bijectivity during complex remeshing processes, where conventional data transfer methods often induce geometric or attribute distortions. The authors propose a composite mapping framework based on local bijective atlases, enhanced by a Shared Scaffold structure that guarantees global bijectivity. The approach is generalized to support a variety of remeshing operations and, for the first time, enables the construction of bijective mappings on 3D tetrahedral remeshings by innovatively integrating Steinitz’s theorem with Maxwell–Cremona lifting theory. This framework facilitates precise tracking of geometric entities—including points, curves, and surfaces—across remeshing sequences, significantly improving fidelity in high-precision applications such as texture transfer and volumetric simulation.

Existing generative design methods suffer from strong data dependency, difficulty in extending to multi-physics scenarios, and low geometric-field coupling accuracy under large deformations. This paper proposes an optimal-transport-based generative design framework that integrates Wasserstein barycenters with Gaussian splatting to enable synchronized, mass-conserving interpolation of geometry and multi-physics fields (scalar and vector) on non-matching meshes and under large deformations. By transcending the limitations of static-mesh surrogate models, the method explicitly preserves localized physical features—such as stress concentrations—thereby significantly improving fidelity and physical consistency in design space exploration. Experimental results demonstrate the framework’s efficiency, robustness, and superiority across diverse scenarios. The approach establishes a new paradigm for high-fidelity, scalable generative design.

This work addresses the high computational cost of geometric mapping under spatially varying fields at high resolutions by proposing a resolution-agnostic neural surrogate model. The method operates without reliance on fixed grids or ground-truth solution labels, leveraging coordinate-augmented multi-resolution field encoding to predict mapping positions at arbitrary point sets. A geometry-aware unsupervised loss is formulated by integrating variational energy, diffusion equilibration, and quasiconformal theory. Experimental results demonstrate that the approach achieves efficient, accurate, and resolution-flexible geometric parameterization in both quasiconformal mapping and density equilibration tasks, significantly enhancing computational efficiency and generalization capability.

Surrogate modeling for high-cost simulators suffers from data scarcity and poor generalizability, especially when transferring knowledge across heterogeneous parameter domains—risking negative transfer. Method: This paper proposes Localized Transfer Learning Gaussian Process (LOL-GP), a framework that leverages related source-system data to enhance target-model accuracy while mitigating negative transfer induced by parametric domain discrepancies. Its core innovation is a Bayesian latent-variable regularization mechanism, which adaptively identifies transferable versus non-transferable parameter subspaces via Gibbs sampling, enabling fine-grained, localized knowledge transfer. Contribution/Results: LOL-GP overcomes the limited generalizability of conventional transfer learning in scientific simulation and supports multi-source and multi-fidelity data integration. Numerical experiments and a jet turbine design case study demonstrate that LOL-GP achieves significantly higher predictive accuracy and more reliable uncertainty quantification than state-of-the-art surrogate modeling approaches.

Existing 3D Gaussian splatting-based style transfer methods are largely confined to color stylization and often neglect geometric adaptation, leading to inconsistencies in the overall scene structure. This work proposes a geometry-aware joint transfer framework that, for the first time, simultaneously optimizes appearance and geometric features within 3D Gaussian splatting. The approach employs a decoupled optimization strategy that alternately updates color and geometry parameters, complemented by a Geometry-aware Contrastive Feature Matching (GCFM) mechanism that integrates RGB, depth, and edge information for contrastive learning. By explicitly aligning geometric structure with visual style, the method effectively mitigates interference between color and geometry updates. Extensive experiments demonstrate that our approach significantly outperforms existing techniques both qualitatively and quantitatively, achieving high-fidelity style transfer with consistent 3D structural integrity.

Existing methods struggle to generate long, parameterized CAD sequences with complex geometric and topological dependencies, while Transformer-based approaches are hindered by quadratic attention costs and limited context length. This work proposes the first end-to-end diffusion framework based on state space models, encoding CAD programs as hierarchical tree structures and modeling them within a joint geometric-topological state space. We introduce a lightweight C-Mamba module to efficiently capture long-range dependencies and develop a structure-aware diffusion mechanism. To support comprehensive evaluation, we release DeepCAD-240, a new benchmark dataset featuring sequences of up to 240 command steps. Experiments demonstrate that our method significantly outperforms existing Transformer models in both short and long sequence generation, achieving state-of-the-art performance in geometric fidelity and topological consistency.

This study addresses the challenge that existing automated map generalization methods struggle to jointly preserve spatial similarity and cartographic legibility across multiple scales, often treating similarity assessment, constraint modeling, and parameter optimization in isolation. To overcome this limitation, the authors propose a unified similarity-driven framework that formulates map generalization as a constrained multi-scale similarity optimization problem. For the first time, geometric, structural, and learned similarity measures are integrated into the objective function, while cartographic constraints—including legibility, smoothness, and geometric validity—are incorporated through line simplification algorithms. Experimental results demonstrate that the approach adaptively and consistently optimizes parameter configurations across diverse algorithms and scales, achieving high-quality map abstraction that maintains spatial similarity while significantly improving the interpretability and generalizability of parameter control.