SinoTechIntel Academic Portal
Official PDF TranslationChinese Journal of Mechanical Engineering

Learning to Predict 3D Meshes from a Single Image via Depth Consistency

Authors: Hao Huang; Shaoli Liu; Jianhua Liu; Peng Jin

DOI: 10.1186/s10033-025-01335-2Status: Verified Translated Edition
Sponsored AdvertisementAd Placement Area
reCAPTCHA Bot Shield Active

Preparing Secure Academic Download

Verifying human reader & generating high-resolution document...

Verifying Document Integrity15s remaining
← Back to Article
Protected by Google reCAPTCHA v3.PrivacyTerms
Sponsored ContentAdSense In-Feed Ad Slot

Key Findings in This Report

• Introduces a novel single-image 3D mesh reconstruction method that leverages depth consistency without requiring viewpoint pose annotations, overcoming limitations of silhouette-based supervision. • Employs standard deviation and Laplacian losses to regulate mesh edge distribution, leading to more precise reconstructions with finer structural details. • Demonstrates superior performance on both synthetic and real-world datasets, outperforming existing view-based 3D reconstruction methods. • Provides a practical solution for applications in robotics, autonomous driving, and 3D animation by enabling accurate 3D shape inference from a single perspective.