SATO generates artist-quality meshes by ordering tokens as triangle-strip chains that encode UV boundaries, enabling unified triangle/quad outputs and outperforming prior methods in quality and coherence.
Mesh silksong: Auto-regressive mesh generation as weaving silk
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
years
2026 8representative citing papers
An end-to-end 3D editing framework achieves high-fidelity local edits from coarse bounding boxes and 2D image prompts using region-aware loss reweighting and a large-scale parts-derived training dataset.
MeshFlow uses a contrastive MeshVAE for compact mesh latents and a flow transformer for parallel generation, claiming 18x speedup over autoregressive methods with high accuracy on standard metrics.
Adaptive saliency-guided supervoxel tokenization cuts 3D AR token length to 12.8% of uniform voxels while claiming SOTA quality and ~10× speedup on Trellis-500K.
TOPOS creates high-fidelity 3D heads with fixed industry topology from single images via a specialized VAE with Perceiver Resampler and a rectified flow transformer.
MeshWeaver uses sparse-voxel guidance for autoregressive surface weaving to achieve 18% compression and generate up to 16K-face meshes with improved fidelity.
SynVA toolkit generates realistic vascular meshes and anatomically plausible aneurysms, releasing 50,000 labeled samples for medical vision tasks.
QuadLink generates anisotropic quad-dominant meshes from point clouds via autoregressive anchor prediction and centroid-conditioned linking, with a Tri-to-Quad data converter and quad-first assembly.
citing papers explorer
-
Strips as Tokens: Artist Mesh Generation with Native UV Segmentation
SATO generates artist-quality meshes by ordering tokens as triangle-strip chains that encode UV boundaries, enabling unified triangle/quad outputs and outperforming prior methods in quality and coherence.
-
EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning
An end-to-end 3D editing framework achieves high-fidelity local edits from coarse bounding boxes and 2D image prompts using region-aware loss reweighting and a large-scale parts-derived training dataset.
-
MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer
MeshFlow uses a contrastive MeshVAE for compact mesh latents and a flow transformer for parallel generation, claiming 18x speedup over autoregressive methods with high accuracy on standard metrics.
-
SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation
Adaptive saliency-guided supervoxel tokenization cuts 3D AR token length to 12.8% of uniform voxels while claiming SOTA quality and ~10× speedup on Trellis-500K.
-
TOPOS: High-Fidelity and Efficient Industry-Grade 3D Head Generation
TOPOS creates high-fidelity 3D heads with fixed industry topology from single images via a specialized VAE with Perceiver Resampler and a rectified flow transformer.
-
MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation
MeshWeaver uses sparse-voxel guidance for autoregressive surface weaving to achieve 18% compression and generate up to 16K-face meshes with improved fidelity.
-
SynVA: A Modular Toolkit for Vessel Generation and Aneurysm Editing
SynVA toolkit generates realistic vascular meshes and anatomically plausible aneurysms, releasing 50,000 labeled samples for medical vision tasks.
-
QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning
QuadLink generates anisotropic quad-dominant meshes from point clouds via autoregressive anchor prediction and centroid-conditioned linking, with a Tri-to-Quad data converter and quad-first assembly.