adaptive mesh refinement

To address the challenge in surface remeshing where Centroidal Voronoi Tessellation (CVT) struggles to balance mesh quality and computational efficiency, this paper proposes a curvature-adaptive multi-round primal patch clipping CVT framework. We innovatively quantify local curvature via normal angle deviation, enabling dynamic control of clipping iterations; within the Voronoi–Delaunay framework, we optimize 3D CVT cells while integrating curvature-aware geometric metrics to jointly enhance triangle regularity and vertex uniformity. Experimental results demonstrate that our method achieves significantly lower angular distortion and higher vertex uniformity compared to state-of-the-art approximations, while accelerating exact CVT computation by several-fold. Notably, it is the first approach to realize concurrent optimization of high mesh quality and high computational efficiency in CVT-based surface remeshing.

This work addresses a critical bottleneck in dynamic adaptive mesh refinement (AMR) on three-dimensional hybrid meshes containing tetrahedral and hexahedral elements: the inefficient handling of pyramid elements due to the absence of an effective connectivity mechanism and hierarchical tree-based management. The paper presents the first Morton-type space-filling curve tailored for pyramid elements, establishing a comprehensive framework that supports both element-level and forest-level refinement while consistently resolving hanging edges across heterogeneous element types. By introducing a forest-of-refinement-trees data structure, parallel refinement/coarsening algorithms, partitioning strategies, and face-based ghost exchange techniques, the authors develop a highly efficient and scalable AMR system for hybrid meshes. Experimental results demonstrate excellent performance and strong scalability in large-scale parallel environments, significantly extending the applicability of tree-based AMR frameworks to complex hybrid grid configurations.

This study addresses the inefficiency of computational resource allocation in existing adaptive mesh refinement methods, which lack semantic awareness and region-specific control. We propose a neural adaptive triangular mesh refinement approach based on a locally conditioned autoregressive architecture. A key contribution is a novel mesh tokenizer that enables multi-trajectory upsampling generation, facilitating precise local manipulation of both topology and geometry. Experimental results demonstrate that the method preserves global structural integrity while introducing geometric details to user-selected regions. Furthermore, it supports view-dependent refinement and physics-aware optimization, overcoming the limitations of global generation approaches that lack regional controllability. This work significantly enhances the flexibility and efficiency of mesh generation.

Real-time simplification of large-scale polygonal meshes faces an inherent trade-off between computational speed and geometric fidelity. Method: We propose a curvature-guided simplification algorithm based on reverse refinement, departing from conventional top-down simplification paradigms. Inspired by splitting strategies in vector quantization, our approach begins with a coarse initial approximation and progressively refines it via curvature-driven hierarchical subdivision coupled with rigorous error control. This enables guaranteed output under time constraints and high-fidelity rendering at interactive frame rates. Contribution/Results: Experimental evaluation on ultra-large-scale models demonstrates significant improvements over state-of-the-art methods: our algorithm generates shape-preserving, low-distortion approximations within single-frame milliseconds—achieving unprecedented balance between efficiency and geometric accuracy.

Existing 3D generative methods suffer from slow optimization, irregular topology, noisy surfaces, and limited editability. To address these challenges, we propose the first 3D-native diffusion framework supporting both text and image conditioning, enabling second-level generation of topologically regular coarse meshes. Our method introduces multi-view joint conditional modeling and latent-space set representation to enhance geometric consistency across views. Furthermore, we pioneer a normal-field-driven geometric refinement mechanism that enables automated detail enhancement and intuitive, interactive user editing. Extensive experiments demonstrate that our approach significantly outperforms state-of-the-art methods in both qualitative and quantitative evaluations—producing high-fidelity, geometrically coherent meshes with rich surface details and flexible, real-time editability. The code and pretrained models are publicly released and seamlessly integrated into practical 3D modeling workflows.

This work addresses the challenge of watertight remeshing for meshes with complex topology, single-layer structures, or large missing regions, where existing methods often fail to infer globally consistent inside–outside partitions from local geometry, leading to volume-inconsistent pseudo-watertight reconstructions such as double-shell artifacts. We propose the first approach that rigorously formulates watertight remeshing as a voxel labeling problem, building a binary labeling model over a Delaunay tetrahedralization and achieving globally consistent watertight surface reconstruction through graph-cut energy minimization with one-sided constraints. The method inherently guarantees watertightness, effectively suppresses double-shell artifacts, and eliminates unsupported boundaries via a weighted interface penalty term. Extensive evaluations on CelloScan, CelloFill, and ModelNet10 benchmarks demonstrate significant improvements over state-of-the-art methods, particularly yielding compact and volume-consistent solid reconstructions for complex topologies and single-layer geometries.

本文提出了一种新的两步细化六面体网格生成方法，通过中等平衡条件和ILP算法，解决了高质量六面体网格自动生成的问题，保证了所有六面体具有平面面。

This study addresses the challenges of recovering sparse control cages from dense meshes, including inferring control requirements, missing feature curves, and difficulty in correcting initial results. To overcome these issues, this work proposes a modeler-inspired agent workflow that iteratively optimizes through planning and diagnosis phases. A stateful feedback mechanism is introduced to support repair or rollback decisions by incorporating semantic judgments into the pipeline. To ensure inspectability, the planner avoids directly generating vertices, instead integrating multi-view geometric evidence analysis with tool execution verification. Evaluated on a fixed benchmark queue, the proposed method outperforms automatic remeshing approaches across five metrics, reducing Chamfer-L1 to 0.443% and improving the F-score to 92.78%, thereby achieving highly controllable mesh-to-subdivision surface reconstruction.

Existing methods for surface mesh reconstruction from multi-view images often rely on intermediate representations and post-processing steps, which can introduce geometric artifacts and fragmented structures. Direct optimization of explicit meshes, while appealing, faces significant challenges in adaptive topology handling and maintaining UV coordinate consistency. This work proposes ExMesh, a novel framework that, for the first time, seamlessly integrates discrete topological operations—such as vertex splitting and merging—into a continuous, differentiable optimization pipeline, enabling end-to-end explicit mesh reconstruction. By dynamically preserving UV coordinates during topology updates and supporting coarse-to-fine geometric refinement, ExMesh achieves a favorable balance among reconstruction accuracy, mesh compactness, and computational efficiency, substantially outperforming current state-of-the-art approaches.

This work addresses the challenge of parallelizing the black-box legacy mesh generation software AFLR without modifying its source code. It proposes a pseudo-constrained parallel data refinement approach that partitions the computational domain into subregions, each independently invoking the original serial AFLR executable to perform localized mesh refinement. By integrating runtime load balancing with the Advancing Front Local Reconnection algorithm, the method achieves parallel execution while preserving the black-box nature of AFLR. On a 16-core CPU, the approach yields an approximately 11× speedup with consistently high mesh quality. However, due to constraints imposed by boundary inputs, the resulting mesh volume differs from that of the serial execution, highlighting an inherent limitation in parallelizing such legacy codes.