TriFlow introduces a generative method for creating compact 3D meshes with artist‑like triangle topology directly from input geometry such as signed distance fields. It represents mesh topology as a nearest‑vertex vector field (NVF) over the surface, trains a latent flow‑matching model to synthesize this field, and then clusters surface regions to guide a constrained quadric error metric simplification. The resulting meshes closely match the input geometry while exhibiting structured, artist‑like connectivity, achieving 90% lower Chamfer Distance and an 8× speedup over state‑of‑the‑art learning‑based approaches.
arXiv:2609.37139v1 Announce Type: new Abstract: 3D content generation technology has significantly advanced the work of designers, as well as the 3D printing and gaming industries. However, it remain...
SeamFlow is a new generative framework for 3D surface cutting and UV unwrapping that reformulates the discrete mesh‑cutting problem as continuous flow matching in a high‑dimensional edge‑probability space. By learning a deterministic mapping from a Gaussian prior to a target seam‑probability distribution and using an evolution network to couple local topological tokens with global shape priors, SeamFlow guides smooth probability flow through ODE solving. Compared with existing autoregressive generative methods, SeamFlow improves topology awareness, eliminates 3D spatial projection errors and artificial sequential‑order bias, and achieves exceptional semantic coherence with remarkably low parameterization distortion.
Generating high-quality triangle meshes is essential for film, gaming, and interactive 3D applications. Mainstream methods rely on mesh serialization and autoregressive processes, which stuggles in effective inference and is sensitive to error accumulation.
MeshOctave introduces a novel approach to native mesh generation that replaces sequential autoregressive or heuristic flow models with a parallel, coarse-to-fine paradigm. By defining scales through dyadic spatial grid resolutions, it collapses vertices deterministically and then performs split-and-rewire operations to reconstruct fine topology without serialization. The method employs a scale-conditioned masked-uniform discrete diffusion model, achieving higher geometric fidelity and topological validity while supporting adaptive resolution refinement and mesh subdivision tasks.
MeshCarve introduces a flow‑matching approach that generates artisan meshes entirely within compact latent spaces, separating vertex positions and edge connections to avoid joint encoding issues. It employs a hierarchical sparse transformer backbone with VertexVAE and EdgeVAE, which anchor on discrete vertices to drastically shorten token sequences and use spatial‑aware compression without sacrificing reconstruction quality. The method outperforms state‑of‑the‑art autoregressive and flow‑matching techniques on Objaverse and generalizes to Toys4K, representing one of the first fully compressed latent artisan mesh generators.
arXiv:2610.19777v1 Announce Type: new Abstract: Autoregressive models have proven effective for triangular mesh generation by transforming it into predicting the next face, converting the non-differe...
arXiv:2609.38985v1 Announce Type: new Abstract: Generating compact, artist-style meshes with explicit topology typically relies on autoregressive models which incur prohibitive sequential per-token c...
ToCo-Mesh is a dynamic mesh reconstruction framework that preserves topology consistency while achieving high‑fidelity geometry from multi‑view temporal images. It uses a dual‑mesh representation, coupling a canonical template mesh to time‑varying coarse guide meshes via barycentric parameterization, and applies error‑driven split‑and‑merge operations on the template to refine detail. A Surface‑Aligned 2DGS module anchors flattened Gaussians to mesh faces, using rendered normals to guide fine‑tuning and suppress surface irregularities, resulting in photorealistic rendering.
arXiv:2606.23489v2 Announce Type: replace-cross Abstract: Meshes are among the most common 3D scene representations, but directly generating meshes is challenging because the representation contains...
arXiv:2605. 01171v2 Announce Type: replace-cross Abstract: Despite recent progress, recovering parametric CAD construction sequences from geometric input, such as meshes or point clouds, is a key challenge for design and manufacturing, as existing CAD reconstruction and generation methods are largely restricted to difficult-to-edit formats like meshes or Breps or editable simple sketch-and-extrude pipelines and low-complexity datasets.
Optimizing 3D shapes within the latent spaces of deep generative models is fundamental to computer assisted engineering, yet remains prone to a critical failure mode we term manifold drift: the tendency of gradient-based optimization to move latent vectors away from the manifold of valid shapes. This problem is exacerbated in state-of-the-art 3D shape generative models that operate in increasingly high-dimensional latent spaces where valid shapes occupy a vanishingly small fraction of the full space.
arXiv:2606.07288v2 Announce Type: replace Abstract: Reconstructing surface meshes from multi-view images has remained a core challenge in recent years. Most existing methods, whether implicit or expl...