TetraSDF: Precise Mesh Extraction with Multi-resolution Tetrahedral Grid

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Oh, Seonghun, Uh, Youngjung, Kim, Jin-Hwa
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918211603136512
author Oh, Seonghun
Uh, Youngjung
Kim, Jin-Hwa
author_facet Oh, Seonghun
Uh, Youngjung
Kim, Jin-Hwa
contents Extracting meshes that exactly match the zero-level set of neural signed distance functions (SDFs) remains challenging. Sampling-based methods introduce discretization error, while continuous piecewise affine (CPWA) analytic approaches apply only to plain ReLU MLPs. We present TetraSDF, a precise analytic meshing framework for SDFs represented by a ReLU MLP composed with a multi-resolution tetrahedral positional encoder. The encoder's barycentric interpolation preserves global CPWA structure, enabling us to track ReLU linear regions within an encoder-induced polyhedral complex. A fixed analytic input preconditioner derived from the encoder's metric further reduces directional bias and stabilizes training. Across multiple benchmarks, TetraSDF matches or surpasses existing grid-based encoders in SDF reconstruction accuracy, and its analytic extractor produces highly self-consistent meshes that remain faithful to the learned isosurfaces, all with practical runtime and memory efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16273
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TetraSDF: Precise Mesh Extraction with Multi-resolution Tetrahedral Grid
Oh, Seonghun
Uh, Youngjung
Kim, Jin-Hwa
Computer Vision and Pattern Recognition
Graphics
Extracting meshes that exactly match the zero-level set of neural signed distance functions (SDFs) remains challenging. Sampling-based methods introduce discretization error, while continuous piecewise affine (CPWA) analytic approaches apply only to plain ReLU MLPs. We present TetraSDF, a precise analytic meshing framework for SDFs represented by a ReLU MLP composed with a multi-resolution tetrahedral positional encoder. The encoder's barycentric interpolation preserves global CPWA structure, enabling us to track ReLU linear regions within an encoder-induced polyhedral complex. A fixed analytic input preconditioner derived from the encoder's metric further reduces directional bias and stabilizes training. Across multiple benchmarks, TetraSDF matches or surpasses existing grid-based encoders in SDF reconstruction accuracy, and its analytic extractor produces highly self-consistent meshes that remain faithful to the learned isosurfaces, all with practical runtime and memory efficiency.
title TetraSDF: Precise Mesh Extraction with Multi-resolution Tetrahedral Grid
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2511.16273