BriefGPT.xyz
Jul, 2022
MHR-Net: 从2D视图中多假设重建非刚性形状
MHR-Net: Multiple-Hypothesis Reconstruction of Non-Rigid Shapes from 2D Views
HTML
PDF
Haitian Zeng, Xin Yu, Jiaxu Miao, Yi Yang
TL;DR
MHR-Net 是一种用于从多个2D视角中恢复非刚性物体形状的新方法，它使用确定性基础和随机变形模型来生成多个假设并从中选择最佳重建结果，经过实验证明在 Human3.6M，SURREAL 和 300-VW 数据集上其重建性能优于其他方法。
Abstract
We propose
mhr-net
, a novel method for recovering
non-rigid shapes
from Motion (NRSfM).
mhr-net
aims to find a set of reasonable reconstru
→