uv mapping

Current 3D texture generation heavily relies on manual UV mapping—time-consuming and lacking semantic awareness and visibility considerations. To address this, we propose the first unsupervised, differentiable UV parameterization framework that jointly incorporates semantic consistency and visibility awareness. Our method (1) achieves semantically coherent UV chart decomposition via mesh semantic segmentation and cross-shape semantic alignment; (2) introduces ambient occlusion (AO)-weighted soft seam optimization to implicitly guide cuts toward low-visibility regions; and (3) designs an end-to-end trainable backbone that jointly optimizes UV parameterization and seam distribution. Quantitative and qualitative evaluations across multiple benchmarks demonstrate that our approach significantly reduces visible seam artifacts and substantially improves downstream texture generation quality and visual naturalness. This work establishes a new paradigm for automated, high-fidelity 3D content generation.

This work addresses the limitations of traditional UV parametrization methods, which are prone to poor initialization, local minima, and topological foldovers that compromise mapping validity under a fixed atlas. The authors reformulate the problem as a continuous neural reparameterization task, leveraging an untrained SIREN network to implicitly map vertex features into UV space, with its weights optimized via geometric energy minimization. Key innovations include using Laplace–Beltrami spectral coordinates as input, Tutte residual warm-starting, a C² determinant expansion, an injectivity barrier, and a validity-check fallback mechanism, collectively forming a verification-first robust solver. Experiments demonstrate that the method achieves 42 and 47 flip-free valid parametrizations on Thingi10K and xatlas-cut benchmarks, respectively—all compact atlases being flip-free—and attains 1,000/1,000 strictly locally valid, flip-free UV atlases on the Amara Spatial dataset.

Traditional UV unwrapping methods struggle to simultaneously minimize geometric distortion and satisfy artists’ stylistic preferences, such as straight seams and axis-aligned UV islands. This work formulates UV unwrapping for the first time as an end-to-end flow-matching generative problem, learning a mesh-conditioned transport process that maps noise to artist-style UV layouts, thereby producing diverse, production-ready results. To bridge the gap between geometric fidelity and artistic style, the authors introduce a boundary-aware loss and a model-in-the-loop fine-tuning mechanism. Evaluated on a large-scale professional dataset, the proposed method significantly outperforms existing approaches, generating notably straighter seams and more compact, axis-aligned UV islands while maintaining low distortion—results that achieve strong approval from professional artists.

This study addresses the reliance on manual intervention for seam planning in production-level automatic UV unwrapping of quadrilateral meshes. We propose a training-free agent-based method that leverages vision-language models (VLMs) integrated with domain knowledge. By employing query-based mesh representations and a domain-specific language (DSL), our approach decouples high-level intent planning from low-level edge selection, while introducing a feedback loop mechanism to iteratively refine seams. This design ensures compatibility across backend VLMs and enables scalability to extremely large meshes. Experimental results demonstrate that the proposed method reduces the number of charts by 2.9× and shortens seam length by 1.63×, achieving an 80.9% preference rate among professional artists.

Addressing the challenge of simplifying non-manifold, multiply-connected, and textured triangle meshes, this paper formulates mesh simplification as a 2-dimensional simplicial complex reduction problem—the first such formulation—and introduces a topology-robust edge-collapse framework. Key contributions include: (1) an enhanced quadric error metric adapted to topological changes, ensuring geometric fidelity; (2) a novel texture simplification paradigm that retains only texture colors while decoupling UV layout optimization, thereby eliminating bleeding artifacts entirely; and (3) a color-space-driven texture remapping strategy. The method supports arbitrary topology and level-of-detail (LOD) generation. Comprehensive qualitative and quantitative evaluations, together with user studies, demonstrate consistent superiority over state-of-the-art approaches—significantly improving simplification quality and visual consistency for non-manifold meshes.

本文针对网格纹理压缩中UV映射的局限性，提出了一种基于表面对齐纹理场TexF的方法，通过稀疏体素组织纹理属性，并结合3DNTC技术实现高效压缩。

This work addresses the challenge of generating semantic regions for 3D asset segmentation, which traditionally relies on manual intervention and struggles to integrate into interactive content creation pipelines. The authors propose a human-in-the-loop approach for producing editable semantic texture atlases by leveraging multi-view rendering and interactive 2D segmentation—combining SAM² with Label Studio—and back-projecting the results into UV space. A greedy set cover strategy is employed to select key views, enhancing computational efficiency. This method delivers the first unified, editable semantic atlas tailored for XR and game development workflows, enabling downstream tasks such as material assignment and style transfer. Experiments on eight cultural heritage objects demonstrate its effectiveness in handling complex geometries and accurately identifying fine details, cavities, and weak boundaries that require human refinement.

Existing neural surface representations struggle to simultaneously achieve compactness, explicit formulation, global smoothness, topological generality, and reliable differential quantity computation. This work proposes a novel explicit surface representation that dispenses with neural networks entirely: guided by a user-provided coarse proxy mesh, it optimizes local polynomial mappings at each vertex and seamlessly blends neighboring mappings via one-ring coordinate smoothing to produce a globally smooth and differentiable surface. The method innovatively decouples topology from geometric detail, yielding an intrinsically smooth, parameterization-free surface that is equivariant under rigid transformations and uniform scaling—thereby eliminating seam artifacts and parametrization dependencies common in conventional approaches. Experiments demonstrate its effectiveness across diverse topologies and geometric complexities, achieving a superior balance among compactness, simplicity, accessibility of differential quantities, and representational power.

This work proposes a GPU-accelerated interactive atlas packing method that bridges the gap between real-time performance and high-quality offline approaches. Existing real-time techniques often suffer from excessive chart scaling, while offline methods fail to meet the latency requirements of interactive applications. The proposed method achieves near-offline packing quality in real time by enabling tight layout with balanced arrangement—eliminating inter-chart gaps, adaptively adjusting row widths and orientations, and applying bidirectional (horizontal and vertical) gap compression. It further incorporates two efficient shape approximation models to enhance both packing efficiency and visual fidelity. Experimental results demonstrate that, compared to current interactive methods, the approach significantly reduces scaling artifacts, attains packing quality comparable to offline algorithms, and achieves over two orders of magnitude speedup in runtime performance.

本文提出ExMesh++，通过自适应顶点分割与合并及UV一致性的保持，从多视图图像重建可重照明的UV-PBR网格资产，优化几何、材质和光照。