Lune

ICCV2025顶会

DMesh++: An Efficient Differentiable Mesh for Complex Shapes

Sanghyun Son, Matheus Gadelha, Yang Zhou, Matthew Fisher, Zexiang Xu, Yi-Ling Qiao, Ming C. Lin, Yi Zhou

2025年份
3被引次数
2顶会引用

摘要

Point Cloud Recon. (b) 3D Point Cloud Recon. (b) 3D Multi View Recon.

Figure 1. DMesh++ for complex 2D and 3D shapes. DMesh++ encodes all geometric and topological information into continuous point features. (a) By optimizing these point features, DMesh++ is able to reconstruct complex 2D drawings from sample points. (b) This approach is also applicable to 3D, where it reconstructs the complex geometric structure of DNA from a point cloud. (c) By incorporating additional color features, DMesh++ can reconstruct complex, colored 3D shapes from multi-view images. For each result, the "imaginary" part is rendered in gray, while the "real" part-which defines the final mesh-is rendered in other colors. (Sec. 3.1).

问问这篇 Paper

智能体会读完全文。

Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。

可以从这些问题问起

智能体调用

Luneget_paper_fulltext

在 Lune 里问

免费开始,无需绑卡

lune papers fulltext 893b5ebf-0877-41f7-8848-059b9df557da

引用它的顶会 Paper2

问问它们各自怎么用它

它引用的顶会 Paper22

相关 Paper

黄昏的海面,两侧是细线勾勒的悬崖