arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1503.03167cs.CVcs.GRcs.LGcs.NE
收藏

深度卷积逆图形网络

Deep Convolutional Inverse Graphics Network

Microsoft Research Cambridge(微软研究院剑桥分院)

Tejas D. Kulkarni, Will Whitney, Pushmeet Kohli, Joshua B. Tenenbaum

摘要:

本文介绍了深度卷积逆图形网络(DC-IGN),这是一种学习图像可解释表示的模型。这种表示相对于诸如平面外旋转和照明变化之类的变换被解开。DC-IGN模型由多层卷积和去卷积运算符组成,并使用随机梯度变分贝叶斯(SGVB)算法进行训练。我们提出了一个训练过程,以鼓励图形代码层中的神经元表示特定的变换(例如姿势或光线)。给定一个输入图像,我们的模型可以生成同一对象的新图像,但姿态和光照会发生变化。我们提出了定性和定量的结果模型的效率在学习3D渲染引擎。

英文摘要:

This paper presents the Deep Convolution Inverse Graphics Network (DC-IGN), a model that learns an interpretable representation of images. This representation is disentangled with respect to transformations such as out-of-plane rotations and lighting variations. The DC-IGN model is composed of multiple layers of convolution and de-convolution operators and is trained using the Stochastic Gradient Variational Bayes (SGVB) algorithm. We propose a training procedure to encourage neurons in the graphics code layer to represent a specific transformation (e.g. pose or light). Given a single input image, our model can generate new images of the same object with variations in pose and lighting. We present qualitative and quantitative results of the model's efficacy at learning a 3D rendering engine.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑