We present MeshTailor, the first mesh-native generative framework for synthesizing edge-aligned seams on 3D surfaces. Unlike prior optimization-based or extrinsic learning-based methods, MeshTailor operates directly on the mesh graph, eliminating projection artifacts and fragile snapping heuristics. We introduce ChainingSeams, a hierarchical serialization of the seam graph that orders chains from global structural cuts down to local details in a coarse-to-fine manner, and a dual-stream encoder that fuses topological and geometric context. Leveraging this hierarchical representation and dual-stream vertex embeddings, our MeshTailor Transformer utilizes an autoregressive pointer layer to trace seams vertex-by-vertex within local neighborhoods. Extensive evaluations show that MeshTailor produces more coherent and structurally regular seam layouts compared to recent optimization-based and learning-based baselines.
Figures & tables
Figure 2: Overview of MeshTailor. Left: The dual-stream encoder. The input mesh is processed in parallel: the top stream extracts topological connectivity features H via a Graph Encoder on the mesh topology {V,E} , while the bottom stream samples surface points to extract global shape semantics tokens Z using a pretrained point-cloud encoder (frozen during training). These representations are fused via cross-attention within Transformer Blocks. Right: The autoregressive decoder. At each step, the MeshTailor Transformer conditions on the previously generated sequence (“Seq”) to produce a decoder query. A pointer layer attends to the enhanced vertex embeddings H~ to select the next vertex (green box), which is appended to the sequence. The resulting seam chains partition the mesh into UV charts, visualized here with checkerboard texturing to show low distortion, color-coded charts, and the final 2D UV layout.
Figure 3: Canonical ordering of seam chains (coarse-to-fine). We serialize an unordered seam set into a deterministic sequence for autoregressive training/inference with a loops-first, balance-first, large-patch-first strategy: we prioritize loop cuts over open chains, repeatedly select the largest remaining surface patch, and within that patch choose the loop cut that best balances the two resulting sub-patch areas (see Supplemental Material B.2 for details). The example shows how primary loop cuts (e.g., around the neck) are placed first to decompose the shape, followed by finer loops on smaller parts (legs, tail, ears), yielding the final ordered chain list and token sequence τ .
Figure 4: Step-by-step seam generation as mesh traversal. Our autoregressive decoder traverses the input mesh connectivity, selecting the next vertex from the current 1-ring neighborhood. This local constraint makes the predicted seams mesh-native and avoids invalid jumps across the surface.
Figure 5: Seam layout and area distortion comparison on GarmentCodeData [ 14 ] . For each method, we show the predicted seams on the 3D mesh (left) and the corresponding area distortion heatmap on the UV layout (right). While prior methods often produce fragmented or jagged cuts that lead to irregular UV islands, MeshTailor generates cleaner, garment-aligned seam structures with coherent chains and loops, resulting in more regular, compact UV charts while maintaining competitive distortion. Different colors in our seam visualizations indicate distinct seam chains (and loop cuts), highlighting the structured and editable output of our representation.
TexVerse
Method
Overall Dist ↓
Angular Dist ↑
# Charts ↓
Island Compact ↑
Island Convex ↑
SeamLen /Area ↓
Boundary Jagged ↓
Blender
1.182
0.753
48.893
0.287
0.753
6.356
1.313
xatlas
1.087
0.975
47.100
0.412
0.752
6.785
1.092
PartUV
1.134
0.953
16.248
0.385
0.742
4.195
1.061
OptCuts
1.139
0.887
1.6
0.309
0.739
2.190
1.192
Nuvo∗
4.749
0.846
6.42
0.583
0.854
5.628
1.448
Table 1: Quantitative comparison on TexVerse and GarmentCodeData. Note that Nuvo is evaluated on 100 randomly sampled meshes due to runtime, while all other methods use the full test set. We additionally report GT on both datasets, where GT denotes seams extracted from the dataset UV layouts and is shown only as an extra reference. For each metric, the top-3 results among the compared methods are highlighted as best , second , and third .
Figure 6: Seam layout and UV area distortion comparison on TexVerse [ 53 ] . We qualitatively compare MeshTailor with OptCuts, xatlas, Nuvo, Blender Smart UV Project, and PartUV on diverse assets from TexVerse. Compared to existing baselines that often produce fragmented charts or jagged cut boundaries, MeshTailor generates cleaner, mesh-aligned seams with coherent long-range chain/loop structures while maintaining competitive distortion. Different colors in our results denote distinct seam chains/loops, highlighting the structured and editable seam representation.
Figure 7: Left: pairwise preference rates between methods, where each entry reports the fraction of participants favoring the row method over the column method. Right: overall ranking by average win-rate against all other methods. MeshTailor is consistently preferred over all baselines.
Figure 8: UV quality under a tiling stripe texture. Fragmented charts and irregular boundaries often cause stripe discontinuities and misalignment, while MeshTailor preserves coherent regions with consistent texture flow.
Figure 9: Production-oriented UV usability. (a) Our UV layout supports diverse texture appearances on the same garment. (b) Stripe tiling, showing results from prior methods.
Figure 10: MeshTailor naturally produces loop cuts as part of its seam structure. Applying the predicted loops (middle), we recursively split the input mesh into connected patches with clean, artist-like boundaries, yielding a part decomposition (right) that is directly usable for downstream asset processing.
Figure 11: MeshTailor generalizes to meshes at different levels of granularity, handling meshes with more triangles than those seen during training.
Figure 12: We perturb the input mesh by adding Gaussian noise to vertices with increasing σ . Predicted seams remain stable when σ<0.010 and gradually degrade as σ increases, with noticeable extra local cuts at σ=0.0125 .
Figure 13: Divide-and-conquer inference. Starting from a high-resolution mesh, MeshTailor predicts a major seam loop to split the surface into disconnected components, then recursively applies the same seam-tracing process to each sub-mesh. This recursion progressively decomposes the asset into semantically coherent parts, yielding clean, edge-aligned seams and the corresponding UV charts.
Figure 14: Ablation on seam generation. Encoder ablations (w/o EncG , w/o EncP ) and coordinate-based baselines (Coord-Edge/Coord-Chain) versus our full method. Coordinate prediction yields irregular boundaries from required snapping.
Appendix figures & tables8 assets
Supplementary material from the paper’s appendix.
Appendix
Figure 15: Triangle-count distribution of TexVerse part-level training samples. Histogram of triangle counts across the part-level samples retained after the preprocessing rules described in Sec. A.1 .
Figure 16: Graph Encoder. We embed each vertex with coordinate-based point features and apply a stack of GraphSAGE layers with SiLU and LayerNorm to aggregate neighborhood information, producing per-vertex connectivity-aware embeddings used for seam generation.
Figure 17: Coordinate-to-mesh projection. Coordinate-based seams can look plausible in Euclidean space, but snapping them to the input mesh often induces jagged boundaries and may collapse onto the wrong surface sheet under nearby/interpenetrating geometry, leading to disconnections.
Figure 18: User study interface. We present participants with paired seam layout results (including seam visualizations on the 3D mesh and the corresponding UV maps) and ask them to choose the higher-quality option in a 2AFC setting, following the provided criteria (minimization, concealment, and geometry awareness).
Figure 19: Failure cases. (a) Hair and spiky assets. (b) Extremely low-poly meshes. (c) Decoding errors can derail a chain (red arrows).
Figure 20: UV layout comparison on GarmentCodeData. Each island is shown with a unique color to reveal chart fragmentation and boundary regularity.
Figure 21: UV layout comparison on TexVerse. Each island is shown with a unique color to reveal chart fragmentation and boundary regularity.
Figure 22: Additional qualitative results. MeshTailor produces coherent seam layouts across diverse categories and shapes. Colored curves denote different predicted seam chains overlaid on the input meshes.
3D surface cutting and UV unwrapping are fundamental problems in computer graphics. Traditional geometric optimization methods mainly focus on reducing parameterization distortion, but they often overlook visual semantic coherence in seam layouts. Recent autoregressive generative methods improve semantic coherence, yet limited perception of mesh topology often causes inaccurate local cuts. To address these limitations, we introduce SeamFlow, a novel generative framework for 3D surface cutting. We reformulate the discrete mesh-cutting problem as continuous flow matching in a high-dimensional edge-probability space. Through continuous relaxation, SeamFlow learns a deterministic mapping from a Gaussian prior to a target seam-probability distribution. An evolution network couples local topological tokens with global shape priors and guides smooth probability flow through Ordinary Differential Equation solving. Compared with existing autoregressive generative frameworks, SeamFlow improves topology awareness through edge tokenization while eliminating both 3D spatial projection errors and artificial sequential-order bias. Extensive experiments demonstrate that SeamFlow achieves exceptional semantic coherence and remarkably low parameterization distortion. The project page is https://meshy-dev.github.io/seamflow.
Yuming Zhao, Zangyueyang Xian, Qijian Zhang +4
Meshy AI, USA · Nanyang Technological University, Singapore
UV seam placement is a critical yet labor-intensive step in 3D content creation, requiring artists to balance chart shape, seam concealment, and alignment with semantic and geometric features. Existing automatic methods are primarily based on per-object optimization, relying on handcrafted objectives to avoid distortion or on proxies from pretrained models to inject semantic information. However, these strategies are not always well aligned with seams used in industrial production pipelines, often resulting in layouts that deviate from artist-preferred seam patterns and practical production requirements. To address these limitations, we propose SeamGen, a generative model for UV seam generation that aligns with artist preferences and production requirements. Instead of depending on manually designed objectives and constraints, SeamGen learns the distribution of per-edge seam labels from a large corpus of existing seam layouts using a flow-matching generative model. A key challenge is that typical Transformer architectures used in flow matching models are designed for sequential representations, such as point clouds, and cannot naturally account for mesh topology. To enable mesh-native learning, we design a Mesh Transformer backbone that interleaves local graph attention over mesh edges with global self-attention across vertices, capturing both fine-grained geometric cues and long-range topological coherence. To further improve inference-time controllability and quality, we exploit the training-free inpainting capability of flow models for both localized seam refinement and constraint-guided seam generation. Extensive experiments show that by learning priors from professional seam layout data, SeamGen produces UV layouts that better align with artist-authored preferences and achieve superior perceptual quality compared with distortion-based and semantic-proxy baselines.
Hao Xu, Yuqing Zhang, Yiqian Wu +5
State Key Lab of CAD&CG, Zhejiang University · VAST
We present MeshQuery, a training-free agentic approach to automatic UV unwrapping of production-grade quad meshes. A Vision-Language Model (VLM) plans artist-aligned seams using a set of edge-selection tools, conditioned on domain-specific UV-unwrapping knowledge expressed in natural language and refined with a feedback loop. We design a queryable mesh representation together with a domain-specific language (DSL) that enables the agent to retrieve mesh information on demand, express a seam plan as a compact program of edge-selection operators over topological, geometric, and semantic mesh attributes, and iteratively refine it from UV quality feedback. On Adobe Substance 3D and Toys4K meshes, MeshQuery produces 2.9x/4.29x fewer charts and 1.63x/1.7x shorter seams than the strongest baseline, and professional artists prefer its results in 80.9% of comparisons. Ultimately, decoupling high-level intent planning from low-level edge selection and compact mesh representation lets MeshQuery run on different backend VLMs and scale to meshes an order of magnitude larger than autoregressive seam prediction