当前位置:
X-MOL 学术
›
arXiv.cs.GR
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction
arXiv - CS - Graphics Pub Date : 2019-11-20 , DOI: arxiv-1911.09204 Jiongchao Jin, Akshay Gadi Patil, Zhang Xiong, Hao Zhang
arXiv - CS - Graphics Pub Date : 2019-11-20 , DOI: arxiv-1911.09204 Jiongchao Jin, Akshay Gadi Patil, Zhang Xiong, Hao Zhang
We introduce a differential visual similarity metric to train deep neural
networks for 3D reconstruction, aimed at improving reconstruction quality. The
metric compares two 3D shapes by measuring distances between multi-view images
differentiably rendered from the shapes. Importantly, the image-space distance
is also differentiable and measures visual similarity, rather than pixel-wise
distortion. Specifically, the similarity is defined by mean-squared errors over
HardNet features computed from probabilistic keypoint maps of the compared
images. Our differential visual shape similarity metric can be easily plugged
into various 3D reconstruction networks, replacing their distortion-based
losses, such as Chamfer or Earth Mover distances, so as to optimize the network
weights to produce reconstructions with better structural fidelity and visual
quality. We demonstrate this both objectively, using well-known shape metrics
for retrieval and classification tasks that are independent from our new
metric, and subjectively through a perceptual study.
中文翻译:
DR-KFS:用于 3D 形状重建的可微视觉相似性度量
我们引入了一种差分视觉相似性度量来训练深度神经网络进行 3D 重建,旨在提高重建质量。该指标通过测量从形状不同地渲染的多视图图像之间的距离来比较两个 3D 形状。重要的是,图像空间距离也是可微分的,可以测量视觉相似性,而不是像素级失真。具体来说,相似性是由从比较图像的概率关键点图计算的 HardNet 特征的均方误差定义的。我们的差分视觉形状相似度度量可以轻松插入各种 3D 重建网络,取代它们基于失真的损失,例如倒角或地球移动距离,从而优化网络权重以产生具有更好结构保真度和视觉质量的重建。我们客观地证明了这一点,使用众所周知的形状度量来进行独立于我们的新度量的检索和分类任务,并通过感知研究主观地证明这一点。
更新日期:2020-04-02
中文翻译:
DR-KFS:用于 3D 形状重建的可微视觉相似性度量
我们引入了一种差分视觉相似性度量来训练深度神经网络进行 3D 重建,旨在提高重建质量。该指标通过测量从形状不同地渲染的多视图图像之间的距离来比较两个 3D 形状。重要的是,图像空间距离也是可微分的,可以测量视觉相似性,而不是像素级失真。具体来说,相似性是由从比较图像的概率关键点图计算的 HardNet 特征的均方误差定义的。我们的差分视觉形状相似度度量可以轻松插入各种 3D 重建网络,取代它们基于失真的损失,例如倒角或地球移动距离,从而优化网络权重以产生具有更好结构保真度和视觉质量的重建。我们客观地证明了这一点,使用众所周知的形状度量来进行独立于我们的新度量的检索和分类任务,并通过感知研究主观地证明这一点。