REVIEW 35 cited by
Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scale
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Meshes are fundamental representations of 3D surfaces. However, creating high-quality meshes is a labor-intensive task that requires significant time and expertise in 3D modeling. While a delicate object often requires over $10^4$ faces to be accurately modeled, recent attempts at generating artist-like meshes are limited to $1.6$K faces and heavy discretization of vertex coordinates. Hence, scaling both the maximum face count and vertex coordinate resolution is crucial to producing high-quality meshes of realistic, complex 3D objects. We present Meshtron, a novel autoregressive mesh generation model able to generate meshes with up to 64K faces at 1024-level coordinate resolution --over an order of magnitude higher face count and $8{\times}$ higher coordinate resolution than current state-of-the-art methods. Meshtron's scalability is driven by four key components: (1) an hourglass neural architecture, (2) truncated sequence training, (3) sliding window inference, (4) a robust sampling strategy that enforces the order of mesh sequences. This results in over $50{\%}$ less training memory, $2.5{\times}$ faster throughput, and better consistency than existing works. Meshtron generates meshes of detailed, complex 3D objects at unprecedented levels of resolution and fidelity, closely resembling those created by professional artists, and opening the door to more realistic generation of detailed 3D assets for animation, gaming, and virtual environments.
Forward citations
Cited by 35 Pith papers
-
PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation
PolyFlow converts discrete meshes to continuous per-vertex representations using a topology embedder and applies flow matching for parallel artist-style mesh generation that outperforms autoregressive baselines on Toy...
-
MeshFlow: Mesh Generation with Equivariant Flow Matching
MeshFlow applies equivariant optimal-transport flow matching to generate triangle meshes as soups, matching autoregressive quality with an 18x inference speedup.
-
TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields
TriFlow synthesizes nearest-vertex vector fields via flow-matching to generate artist-like 3D mesh topology, then extracts meshes via clustering and topology-aware QEM simplification.
-
BrepForge: Factorized B-rep Synthesis via Wireframe Composition and Boundary-Conditioned Surface Instantiation
BrepForge factorizes B-rep synthesis into face-aware autoregressive wireframe composition followed by boundary-conditioned surface instantiation using learning-free geometric priors.
-
QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning
QuadLink generates anisotropic quad-dominant meshes from point clouds via anchor prediction, centroid-conditioned linking, and quad-first assembly, supporting hybrid n-gon topology.
-
LottieGPT: Tokenizing Vector Animation for Autoregressive Generation
LottieGPT tokenizes Lottie animations into compact sequences and fine-tunes Qwen-VL to autoregressively generate coherent vector animations from natural language or visual prompts, outperforming prior SVG models.
-
AvatarPointillist: AutoRegressive 4D Gaussian Avatarization
AvatarPointillist autoregressively generates adaptive 3D point clouds via Transformer for photorealistic 4D Gaussian avatars from one image, jointly predicting animation bindings and using a conditioned Gaussian decoder.
-
Surface Quadrilateral Meshing from Integrable Odeco Fields
A finite-element method extends 2D odeco integrability to 3D surfaces to generate shear-free quadrilateral meshes with automatic singularity placement and minimized area or stretch distortion under alignment and sizin...
-
PartDiffuser: Part-wise 3D Mesh Generation via Discrete Diffusion
PartDiffuser is a semi-autoregressive discrete diffusion framework that generates high-fidelity 3D meshes from point clouds by combining inter-part autoregression with intra-part parallel diffusion using a part-aware ...
-
Meshy T2: Fast Native Mesh Generation with Flow Matching
Single-image native mesh generation runs at interactive speed in Meshy T2 by flow-matching one continuous latent per vertex, then decoding vertices, edge connectivity, and face winding in one pass.
-
Nexus: Native Mesh Generation with Diffusion
Nexus replaces autoregressive mesh serialization with two coupled diffusion models — octree vertex generation and a latent topology generator — claiming stronger geometry and perceptual quality on Objaverse and Toys4K.
-
LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow
Factorizing mesh generation into a vertex flow then a vertex-conditioned topology flow improves fidelity and enables part-wise high-res synthesis and topology-adaptive editing.
-
Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation
Barycentric Dominance Field converts discrete mesh connectivity into a continuous surface signal that diffusion models can use directly for higher-quality native 3D mesh generation.
-
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.
-
QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning
QuadLink generates anisotropic quad-dominant meshes from point clouds via a hybrid centroid-conditioned vertex linking model and a Tri-to-Quad data conversion operator.
-
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.
-
SQuadGen: Generating Simple Quad Layouts via Chart Distance Fields
SQuadGen generates simple quad layouts on 3D shapes via chart distance fields and diffusion models, outperforming prior remeshing methods on a newly constructed dataset of loop-aware simple meshes.
-
Beyond Voxel 3D Editing: Learning from 3D Masks and Self-Constructed Data
BVE framework enables text-guided 3D editing beyond voxel limits by combining self-constructed data, lightweight semantic injection, and annotation-free masking to preserve local invariance.
-
UniRecGen: Unifying Multi-View 3D Reconstruction and Generation
UniRecGen unifies reconstruction and generation via shared canonical space and disentangled cooperative learning to produce complete, consistent 3D models from sparse views.
-
Twisted Fiber Bundle Codes over Group Algebras
Singular chain-compatible fiber twists over group algebras can increase CSS encoded dimension k at fixed blocklength n while examples keep distance d unchanged.
-
LL3M: Large Language 3D Modelers
A multi-agent LLM system generates editable 3D assets as Blender Python code, using documentation retrieval and visual self-critique to refine results.
-
MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh
MeshLLM improves LLM-based 3D mesh understanding and generation through primitive decomposition, a 1500k+ sample dataset, and topology-focused training strategies.
-
LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow
LATO.2 factorizes mesh generation into a vertex-generation flow and a vertex-conditioned connectivity flow, beating joint-latent and autoregressive baselines on geometric fidelity and connectivity quality.
-
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.
-
AssetGen: Deployable 3D Asset Generation at Interactive Speed
AssetGen is a system that produces deployable 3D assets including meshes, baked normals, and textures from a single reference image in under 30 seconds via a coarse-to-refine VecSet pipeline and co-designed optimizations.
-
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.
-
From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation
The paper surveys 3D asset generation methods and organizes them around the full production pipeline to assess which outputs meet engine-level requirements for interactive applications.
-
MeshOn: Intersection-Free Mesh-to-Mesh Composition
MeshOn composes two input meshes realistically without intersections by using VLM-based rigid initialization, attractive geometric losses, a barrier loss, and a diffusion prior for final deformation.
-
PartDiffuser: Part-wise 3D Mesh Generation via Discrete Diffusion
A part-wise semi-autoregressive discrete diffusion model for point-cloud-to-mesh generation that separates global structure from local detail, beating prior SOTA on Objaverse.
-
XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding
XSpecMesh speeds up auto-regressive mesh generation by about 1.7x using multi-head speculative decoding with cross-attention heads and a probability threshold verification, while keeping output quality close to the ba...
-
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.
-
From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation
The paper surveys 3D content generation literature using a taxonomy of asset types and production stages to evaluate progress toward engine-ready assets.
-
RelMap: Reliable Spatiotemporal Sensor Data Visualization via Imputative Spatial Interpolation
RelMap combines GNN-based imputation with spatial interpolation and uncertainty-aware heatmaps for spatiotemporal sensor data.
-
DreamComposer++: Empowering Diffusion Models with Multi-View Conditions for 3D Content Generation
A multi-view conditioning framework that improves controllable novel view synthesis and 3D reconstruction by injecting fused 3D latents into frozen image and video diffusion models.
-
Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details
Hunyuan3D 2.5's LATTICE model with 10B parameters generates detailed 3D shapes from images and uses multi-view PBR for textures, outperforming prior methods in fidelity and mesh quality.
Discussion (0). Sign in to comment.