PRS: Sharp Feature Priors for Resolution-Free Surface Remeshing

Natalia Soboleva, Olga Gorbunova, Maria Ivanova, Evgeny Burnaev, Matthias Nießner, Denis Zorin, Alexey ArtemovarXiv 2023 · DOI · arXiv

Abstract

Standard 3D reconstruction methods often fail to preserve sharp geometric features, resulting in aliased or rounded edges. We present PRS (Sharp Feature Priors), a data-driven framework that recovers these features by learning local surface-based fields. By predicting distance-to-feature, direction-to-feature, and surface improvement metrics, PRS enables an iterative remeshing process that achieves state-of-the-art accuracy across arbitrary resolutions without manual parameter tuning.

Introduction

In 3D computer vision and CAD, shapes are frequently represented as implicit functions (e.g., Signed Distance Fields) and converted into explicit meshes via algorithms like Marching Cubes. These methods typically struggle with sharp features, producing jagged approximations instead of clean 90-degree edges. While recent neural methods attempt to mitigate this, they are often "resolution-locked" to specific grid sizes. PRS addresses these challenges by providing a resolution-free, automatic pipeline to detect and reconstruct sharp features directly on the mesh.

Overview of the PRS framework, showing the training on geometric datasets to learn surface priors and the subsequent refinement of coarse inputs.

Methodology

The core of PRS lies in three learned surface-based priors predicted on local triangulated patches:

  1. Distance-to-feature ($d$): A scalar field estimating the distance from a vertex to the nearest sharp edge.
  2. Direction-to-feature ($r$): A vector field pointing toward that edge.
  3. Surface improvement ($s$): An edge-based field predicting normal alignment improvement following an edge flip.

The PRS Pipeline

The refinement process follows a structured sequence:

  • Feature Detection: A Dynamic Graph CNN (DGCNN) predicts the vertex-based $d$ and $r$ fields.
  • Vertex Snapping: Vertices near features are "snapped" onto estimated sharp edges using the predicted distance and direction.
  • Connectivity Optimization: A MeshCNN identifies edges for flipping to better align the mesh with the underlying geometry.
  • Scalability: By operating on local patches (~2000 vertices) and fusing results globally, PRS handles meshes of arbitrary complexity.
Detailed breakdown of the PRS pipeline: (a) coarse input, (b) feature guidance fields, (c) vertex snapping, (d) surface improvement field, and (e) the final remeshed shape.

Key Insights

PRS shifts the focus from purely geometric vertex movement to learning connectivity via edge flips. This discrete optimization is guided by a "Surface Improvement" field that targets normal consistency—the key to perceptual sharpness. Furthermore, the patch-based approach ensures resolution independence, allowing the same model to perform effectively on grids ranging from $128^3$ to $512^3$.

Experimental Results

Evaluated on the ABC Dataset (CAD models) and ShapeNet (general objects), PRS significantly outperforms existing baselines:

  • Accuracy: Improved Normals F-score by 26% over Neural Dual Contouring.
  • Perceptual Quality: Reduced perceptual RMSE by 42%.
  • Efficiency: Produces high-quality results using 3x fewer triangles by placing geometry strategically on features.

Conclusion and Future Work

PRS demonstrates a robust method for resolution-free surface refinement. While highly effective, future work may address the "needle in a haystack" problem of identifying useful edge flips in highly refined meshes and explore end-to-end learnable solutions that eliminate remaining heuristic post-processing steps.

Summary updated

Abstract

Surface reconstruction with preservation of geometric features is a challenging computer vision task. Despite significant progress in implicit shape reconstruction, state-of-the-art mesh extraction methods often produce aliased, perceptually distorted surfaces and lack scalability to high-resolution 3D shapes. We present a data-driven approach for automatic feature detection and remeshing that requires only a coarse, aliased mesh as input and scales to arbitrary resolution reconstructions. We define and learn a collection of surface-based fields to (1) capture sharp geometric features in the shape with an implicit vertexwise model and (2) approximate improvements in normals alignment obtained by applying edge-flips with an edgewise model. To support scaling to arbitrary complexity shapes, we learn our fields using local triangulated patches, fusing estimates on complete surface meshes. Our feature remeshing algorithm integrates the learned fields as sharp feature priors and optimizes vertex placement and mesh connectivity for maximum expected surface improvement. On a challenging collection of high-resolution shape reconstructions in the ABC dataset, our algorithm improves over state-of-the-art by 26% normals F-score and 42% perceptual $\text{RMSE}_{\text{v}}$.
BibTeX
@misc{soboleva2023prs,
  author = {Natalia Soboleva and Olga Gorbunova and Maria Ivanova and Evgeny Burnaev and Matthias Nießner and Denis Zorin and Alexey Artemov},
  title = {{PRS: Sharp Feature Priors for Resolution-Free Surface Remeshing}},
  year = {2023},
  eprint = {2311.18494},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.18494},
}
Figure