Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
December 21, 2025Open Access

Geometric Prior-Guided Neural Implicit Surface Reconstruction in the Wild

View Full Paper
Ask AI
Bookmark
Share

Authors

LXLintao XiangHZHuadong ZhengBDBailin Deng

Discussion

Loading...

Member takes

Overview

Our method improves surface reconstruction accuracy in uncontrolled environments using digital preservation techniques and geometric constraints.

Key Points

  • This research aims to improve neural implicit surface reconstruction in complex, uncontrolled environments.
  • Applied geometric constraints to implicit surface optimization.
  • Utilized sparse 3D points from structure-from-motion for signed distance function refinement.
  • Employed normal priors and filtering techniques for improved surface alignment.
  • Achieved superior accuracy and granularity in surface reconstructions compared to existing methods.
  • Successfully reconstructed 3D geometries of various landmarks from in-the-wild images.

Cite This Study

Xiang et al. (2025) studied this question.

synapsesocial.com/papers/69473b64db9c958d0dfca8a7https://doi.org/10.48550/arxiv.2505.07373
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views2024 · 25 citations
  2. 2Normal-guided Detail-Preserving Neural Implicit Functions for High-Fidelity 3D Surface Reconstruction2024 · 1 citations
  3. 33D Reconstruction of Indoor Scenes Based on Neural Implicit2024
  4. 4MF‐SDF: Neural Implicit Surface Reconstruction using Mixed Incident Illumination and Fourier Feature Optimization2025
  5. 5Neural implicit surfaces learning for multi-view reconstruction2024