mesh-generation

T3lescope提出一种单一固定分辨率生成器的推理时粗到细级联方法，从多视角图像实现跨尺度（从单物体到大型户外场景）的任意分辨率高保真3D场景网格重建，无需逐场景优化，在室内、户外和城市规模场景上超越了前馈与生成基线。

This paper presents a reinforcement learning agent trained to generate provably optimal quadrilateral block decompositions for planar domains, demonstrating superior performance over existing tools like Gmsh in terms of usability and optimality.

WorldSculpt is a framework that reconstructs cluttered scenes from grounded videos into compositional per-object meshes, enabling interactive 3D world generation and editing.

Meshy T2 introduces a fast native mesh generation framework using flow matching and a vertex-set mesh VAE, achieving state-of-the-art geometric fidelity with end-to-end image-to-mesh generation in a median of 6 seconds, over an order of magnitude faster than autoregressive baselines.

PolyFlow introduces a continuous mesh representation using a topology embedder and applies flow-matching with Transformers for parallel mesh generation, achieving faster inference and precise resolution control compared to autoregressive methods.

MeshFlow introduces an equivariant optimal-transport flow matching model for direct triangle mesh generation, achieving state-of-the-art quality while providing approximately 18x inference speedup over autoregressive methods.

JanusMesh is a fast, training-free framework that generates text-driven 3D visual illusions—a single mesh revealing different semantics from different viewing angles—by decoupling generation into cross-space dual-branch denoising and view-conditioned texture synthesis, achieving high realism in just 3-5 minutes.

MeshWeaver presents an autoregressive mesh generation framework that directly predicts vertices using a multi-level sparse-voxel encoder, achieving state-of-the-art compression and geometric fidelity for high-poly meshes.

A training-free 4D mesh generation approach using Spatio-Temporal Attention Chains accelerates creation to 9 seconds (13x speedup) while improving temporal consistency and scaling to longer sequences, with zero-shot capabilities for tracking and camera estimation.

This paper introduces a triangulation-agnostic flow matching method for mesh-based signal generation, using Matérn processes as noise and PoissonNet as denoiser, achieving high-quality results on large meshes.

A developer ported Microsoft's TRELLIS.2 image-to-3D model to run on Apple Silicon Macs by replacing CUDA-only dependencies with PyTorch MPS equivalents, enabling offline 3D mesh generation without requiring NVIDIA GPUs.

A community port of Microsoft's TRELLIS.2 image-to-3D generation model to run natively on Apple Silicon Macs via PyTorch MPS, eliminating the need for NVIDIA GPUs and generating high-quality 3D meshes with 400K+ vertices in ~3.5 minutes on M4 Pro.

Spirula Studio is an open-source tool that trains 3D Gaussian Splatting models from raw photos or videos, supporting multiple GPUs via Vulkan with features like VRAM efficiency, native 360° camera support, and built-in SfM and AI masking.