TopoMesh: High-Fidelity Mesh Autoencoding via Topological Unification

• URL: http://arxiv.org/abs/2603.24278v2
• Date: Thu, 26 Mar 2026 05:46:23 GMT
• Title: TopoMesh: High-Fidelity Mesh Autoencoding via Topological Unification
• Abstract summary: TopoMesh is a sparse voxel-based VAE that unifies both GT and predicted meshes under a shared Dual Marching Cubes (DMC) topological framework.<n>Our decoder outputs meshes in the same DMC format, ensuring that both predicted and target meshes share identical topological structures.<n>Extensive experiments demonstrate that TopoMesh significantly outperforms existing VAEs in reconstruction fidelity.
• Score: 44.632513151214084
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The dominant paradigm for high-fidelity 3D generation relies on a VAE-Diffusion pipeline, where the VAE's reconstruction capability sets a firm upper bound on generation quality. A fundamental challenge limiting existing VAEs is the representation mismatch between ground-truth meshes and network predictions: GT meshes have arbitrary, variable topology, while VAEs typically predict fixed-structure implicit fields (\eg, SDF on regular grids). This inherent misalignment prevents establishing explicit mesh-level correspondences, forcing prior work to rely on indirect supervision signals such as SDF or rendering losses. Consequently, fine geometric details, particularly sharp features, are poorly preserved during reconstruction. To address this, we introduce TopoMesh, a sparse voxel-based VAE that unifies both GT and predicted meshes under a shared Dual Marching Cubes (DMC) topological framework. Specifically, we convert arbitrary input meshes into DMC-compliant representations via a remeshing algorithm that preserves sharp edges using an L$\infty$ distance metric. Our decoder outputs meshes in the same DMC format, ensuring that both predicted and target meshes share identical topological structures. This establishes explicit correspondences at the vertex and face level, allowing us to derive explicit mesh-level supervision signals for topology, vertex positions, and face orientations with clear gradients. Our sparse VAE architecture employs this unified framework and is trained with Teacher Forcing and progressive resolution training for stable and efficient convergence. Extensive experiments demonstrate that TopoMesh significantly outperforms existing VAEs in reconstruction fidelity, achieving superior preservation of sharp features and geometric details.

Related papers

• MSVS-VAE: Multi-Scale Anchored VecSet for High-Fidelity 3D Reconstruction [39.69838180175452]
  We propose MSVS-VAE, a hierarchical set-based VAE that closes this fidelity gap without sacrificing compactness.<n>Our key idea is to progressively densify anchored VecSet latents via hierarchical point-shuffle upsampling, increasing spatial capacity for fine-grained geometry modeling.<n>Extensive experiments on generative benchmarks, ABO, and in-the-wild benchmarks demonstrate that MSVS-VAE consistently outperforms prior set-based and voxel-based VAEs, delivering approximately 10x faster decoding than prior set-based methods and approximately 10x higher compactness than voxel-based
  arXiv  Detail & Related papers  (2026-07-27T13:45:22Z)
• ExMesh: EXplicit Mesh Reconstruction with Topology Adaptation [36.887001139824456]
  We propose ExMesh, a novel framework that directly optimize explicit meshes.<n>We show that ExMesh achieves a balance among accuracy and mesh conciseness.
  arXiv  Detail & Related papers  (2026-06-05T13:59:58Z)
• Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization [56.95448807869383]
  Federated Learning (FL) has emerged as a compelling paradigm for privacy-preserving distributed machine learning.<n>Recent studies find that the gradients exchanged in the FL system are also vulnerable to privacy leakage.<n>We propose textbfGradient textbfInversion over textbfFeature textbfDomains (GIFD)
  arXiv  Detail & Related papers  (2026-04-01T14:32:15Z)
• Shape-of-You: Fused Gromov-Wasserstein Optimal Transport for Semantic Correspondence in-the-Wild [7.4746628878102195]
  Shape-of-You is an unsupervised learning framework for semantic correspondence.<n>It achieves state-of-the-art performance on SPair-71k and AP-10k datasets.
  arXiv  Detail & Related papers  (2026-03-12T07:22:03Z)
• LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtents [43.84310366771089]
  LATO is a novel topology-preserving latent representation that enables scalable, flow matching-based synthesis of explicit 3D meshes.<n>For generative modeling, LATO adopts a two-stage flow matching process, first synthesizing the structure voxels and subsequently refining the voxel-wise topology features.<n>Compared to prior isosurface/triangle-based diffusion models and autoregressive generation approaches, LATO generates meshes with complex geometry, well-formed topology while being highly efficient in inference.
  arXiv  Detail & Related papers  (2026-03-06T15:09:25Z)
• DINO-SAE: DINO Spherical Autoencoder for High-Fidelity Image Reconstruction and Generation [47.409626500688866]
  We present the DINO Spherical Autoencoder (DINO-SAE), a framework that bridges semantic representation and pixel-level reconstruction.<n>Our approach achieves state-of-the-art reconstruction quality, reaching 0.37 rFID and 26.2 dB PSNR, while maintaining strong semantic alignment to the pretrained VFM.
  arXiv  Detail & Related papers  (2026-01-30T12:25:34Z)
• Dense Semantic Matching with VGGT Prior [49.42199006453071]
  We propose an approach that retains VGGT's intrinsic strengths by reusing early feature stages, fine-tuning later ones, and adding a semantic head for bidirectional correspondences.<n>Our approach achieves superior geometry awareness, matching reliability, and manifold preservation, outperforming previous baselines.
  arXiv  Detail & Related papers  (2025-09-25T14:56:11Z)
• Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers [59.0181939916084]
  Traditional 3D networks mainly focus on local geometric details and ignore the topological structure between local geometries. We propose a novel Priors Distillation (RPD) method to extract priors from the well-trained transformers on massive images. Experiments on the PointDA-10 and the Sim-to-Real datasets verify that the proposed method consistently achieves the state-of-the-art performance of UDA for point cloud classification.
  arXiv  Detail & Related papers  (2024-07-26T06:29:09Z)
• UGMAE: A Unified Framework for Graph Masked Autoencoders [67.75493040186859]
  We propose UGMAE, a unified framework for graph masked autoencoders. We first develop an adaptive feature mask generator to account for the unique significance of nodes. We then design a ranking-based structure reconstruction objective joint with feature reconstruction to capture holistic graph information.
  arXiv  Detail & Related papers  (2024-02-12T19:39:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.