DINeMo: Learning Neural Mesh Models
with no 3D Annotations

Technical Report

Weijie Guo   Guofeng Zhang   Wufei Ma   Alan Yuille  

Johns Hopkins University  

arXiv

We present DINeMo, a novel neural mesh model that is trained with no 3D annotations by leveraging pseudo-correspondence obtained from large visual foundation models.

DINeMo overview
Figure 1. Overview of our DINeMo model.
DINeMo overview
Figure 2. Bidirectional pseudo-correspondence generation.
DINeMo overview
Figure 3. Qualitative comparisons with and without our bidirectional pseudo-correspondence generation.

BibTeX

@article{guo2025dinemo,   title={DINeMo: Learning Neural Mesh Models with no 3D Annotations},   author={Guo, Weijie and Zhang, Guofeng and Ma, Wufei and Yuille, Alan},   journal={arXiv preprint arXiv:2412.07825},   year={2025} }

Notes

This website template is adapted from Image Sculpting.