Autoregressive models have proven effective for triangular mesh generation by transforming it into predicting the next face, converting the non-differentiable connectivity prediction into a sequence of token predictions. However, generating quad-only meshes remains challenging because quad faces impose stricter topological constraints than triangles. The model must not only serialize quad faces into a valid token sequence, but also support unambiguous connectivity reconstruction during de-serialization. To address this, we propose Q-MAGIC, a novel autoregressive model for quad mesh generation. We first introduce a tailored serialization scheme for quad meshes, which requires at least two new vertices for the next face and is less flexible than triangles due to strict wiring constraints. To meet these requirements and reduce serialization length, we propose a singularity-aware serialization that prioritizes wiring from singular points, leading to more coherent traversals. Additionally, we propose a circular relative offset tokenization that encodes geometry mainly via local relative offsets. Built upon this representation, an autoregressive Transformer learns the underlying distribution of quad meshes via next-token prediction, enabling effective quad mesh generation. Extensive experiments demonstrate that Q-MAGIC produces more compact sequences while consistently improving geometric fidelity and mesh quality compared to state-of-the-art methods.
Figures & tables
Figure 1: Overview of the Q-MAGIC. We adopt a singularity-aware serialization strategy that prioritizes critical singularities in the sequence. In our token representation, geometric information is mainly encoded by circular relative offsets, and block tokens are inserted only when necessary to re-anchor the spatial location, enabling a compact representation. During inference, Q-MAGIC conditions on point clouds and autoregressively generates quad meshes.
Figure 2: Overview of circular relative offset tokenization. Left: each vertex is represented by a block–offset pair (B,O) . Right: For intra-block moves, we emit only Δon (wrapping to the bounded interval when needed); when crossing a block boundary, we emit the new block index B and then continue with relative offsets. Bottom: the resulting token sequence with BOS/EOS, consisting of block tokens and circular relative offset tokens.
Figure 3: De-serialization in Q-MAGIC. (a) Consecutive records recover the shared vertex from the last vertex of the previous face. (b,c) Directly connecting adjacent tokens for non-consecutive records may generate invalid red dashed quads. We resolve this issue via a novel de-serialization scheme. Quads are reconstructed from the recorded non-center vertices under the face of the current local patch, ensuring consistent local topology.
Method
QGPT
MAV2
EG
DM
BPT
Ours
Avg. Len.
43106
29000
28497
20675
14104
12655
Comp. Ratio
1
0.67
0.66
0.48
0.33
0.29
Table 1: Average sequence length comparison. QGPT, MAV2, EG, and DM denote QuadGPT, MeshAnythingV2, EdgeRunner and DeepMesh. Our serialization yields the lowest token length on the same mesh set.
Figure 4: Visualization results and close-up views of generated quad meshes. Our method can better preserve continuous boundary loops and structured quad layouts in detail-sensitive regions, producing more regular and stable quad meshes.
Model
Point2Quad
TMGPT
QuadGPT
BPT
Ours
SJ ↑−11
0.9726
0.8879
0.9727
0.9762
0.9829
WT ↑01
0.9995
0.8921
0.9836
0.9873
0.9996
MF ↑01
1
0.9989
0.9998
0.9998
0.9999
CD ↓0∞
0.0717
0.1704
0.0854
0.0719
0.0684
HD ↓0∞
0.1069
0.3255
0.1374
0.1299
0.1058
SR ↓01
0.3050
0.8715
0.2164
0.4000
0.2310
Table 2: Quantitative comparison. ↑ba and ↓ba denote that larger and smaller values are better, respectively. Here, a and b represent the upper and lower bounds.SJ, WT, MF, CD, HD, SR and US denote Scaled Jacobian, Watertightness, Manifoldness, Chamfer distance, Hausdorff distance, singularity rate and user study.
Metrics
Random
Singularity-aware
Scaled Jacobian ↑−11
0.8862
0.9829
Watertightness ↑01
0.9429
0.9996
Manifoldness ↑01
0.9986
0.9999
Chamfer distance ↓0∞
0.2202
0.0684
Hausdorff distance ↓0∞
0.3906
0.1058
Table 3: Ablation study on patch serialization policies under circular relative offset tokenization (Random vs. singularity-aware).
Metrics
Block-offset
Circ. relative offset
Scaled Jacobian ↑−11
0.7442
0.9829
Watertightness ↑01
0.6635
0.9996
Manifoldness ↑01
0.9993
0.9999
Chamfer distance ↓0∞
0.3161
0.0684
Hausdorff distance ↓0∞
0.5487
0.1058
Table 4: Ablation study on serialization scheme under the default singularity-aware traversal (Circular relative offset vs. Block-offset).
Figure 5: Qualitative ablation on serialization schemes.
Figure 6: Qualitative ablation on patch traversal order.
The generation of production-ready quad-dominant meshes is a cornerstone of modern 3D content creation. Generating anisotropic quad-dominant meshes from point clouds is challenging, as existing methods are typically limited to producing either pure triangular meshes or pure quadrilateral meshes with isotropic densities. In this paper, we present QuadLink, a unified framework consisting of three stages for quad-dominant mesh generation by linking points into structured faces. QuadLink formulates polygonal mesh generation as a hybrid centroid-conditioned vertex linking model: it first predicts a unified set of anchors (vertices and face centroids), then learns centroid-conditioned links that associate vertices with face centroids, and finally assembles polygonal faces with a quad-first strategy guided by robust geometric verification strategies. This link-based formulation enables efficient generation of sparse and anisotropic quad-dominant meshes with coherent edge flow and meanwhile supporting hybrid polygonal topology. To construct training data for this model, we further introduce a Tri-to-Quad Operator that converts artistic triangle meshes into quad-dominant training data via global merge selection. Extensive experiments show that QuadLink produces production-ready quad-dominant meshes from point clouds and achieves improved geometric fidelity and topological quality compared to prior baselines. Our method natively supports hybrid polygonal topology, generalizing to arbitrary n-gon meshes without architectural changes.
Yiheng Zhang, Zhe Zhu, Tingrui Shen +11
Hong Kong University of Science and Technology, Tencent VISVISE, China · Tencent VISVISE, China · Peking University, China +6
Recent advancements in autoregressive transformers have demonstrated remarkable potential for generating artist-quality meshes. However, the token ordering strategies employed by existing methods typically fail to meet professional artist standards, where coordinate-based sorting yields inefficiently long sequences, and patch-based heuristics disrupt the continuous edge flow and structural regularity essential for high-quality modeling. To address these limitations, we propose Strips as Tokens (SATO), a novel framework with a token ordering strategy inspired by triangle strips. By constructing the sequence as a connected chain of faces that explicitly encodes UV boundaries, our method naturally preserves the organized edge flow and semantic layout characteristic of artist-created meshes. A key advantage of this formulation is its unified representation, enabling the same token sequence to be decoded into either a triangle or quadrilateral mesh. This flexibility facilitates joint training on both data types: large-scale triangle data provides fundamental structural priors, while high-quality quad data enhances the geometric regularity of the outputs. Extensive experiments demonstrate that SATO consistently outperforms prior methods in terms of geometric quality, structural coherence, and UV segmentation. Project page: https://ruixu.me/html/SATO/index.html
Rui Xu, Dafei Qin, Kaichun Qiao +8
The University of Hong Kong, Deemos Technology Co., Ltd. , China · ShanghaiTech University, Deemos Technology Co., Ltd., China · Shandong University, China +3
Autoregressive mesh generation has gained attention by tokenizing meshes into sequences and training models in a language-modeling fashion. However, existing approaches suffer from two fundamental limitations: (i) low tokenization efficiency, which yields long token sequences and prevents scaling to high-poly meshes, and (ii) absence of geometry-aware guidance, as generation is conditioned only on global shape embeddings rather than local surface cues. We introduce MeshWeaver, an autoregressive framework that treats mesh generation as a surface weaving process by directly predicting the next vertex instead of independent coordinates. At its core is a multi-level sparse-voxel encoder that injects geometric context into the generative process in three complementary ways: providing voxel features as vertex representations, guiding token prediction via cross-attention to voxel features, and serving as a structural scaffold that constrains generation around the input surface. Our hierarchical design enables coarse-to-fine vertex prediction in a single decoding step, while tightly coupling the generative model with 3D geometry. Extensive experiments demonstrate that MeshWeaver achieves a state-of-the-art compression ratio of 18%, can generate meshes with up to 16K faces, and significantly improves geometric fidelity over prior approaches.