arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1912.04591cs.CVcs.GR
收藏

Neural Voxel Renderer:学习一个精确可控的渲染工具

Neural Voxel Renderer: Learning an Accurate and Controllable Rendering Tool

Google Research(谷歌研究院)

Konstantinos Rematas, Vittorio Ferrari

摘要:

我们提出了一个神经渲染框架,将体素化场景映射到高质量的图像。高度纹理化的对象和场景元素的相互作用,现实地呈现我们的方法,尽管有一个粗略的表示作为输入。此外,我们的方法允许可控渲染:输入中的几何和外观修改准确地传播到输出。用户可以移动,旋转和缩放对象,更改其外观和纹理或修改灯光的位置,所有这些编辑都在最终渲染中表示。我们证明了我们的方法的有效性,通过渲染不同外观的场景,从单一的颜色每个对象复杂的,高频纹理。我们表明,我们的重新渲染网络可以生成非常详细的图像,精确地表示输入场景的外观。我们的实验表明,与替代方案相比,我们的方法实现了更准确的图像合成结果,并且还可以处理低体素网格分辨率。最后,我们展示了我们的神经渲染框架如何从真实图像和不同的类集合中捕获和忠实地渲染对象。

英文摘要:

We present a neural rendering framework that maps a voxelized scene into a high quality image. Highly-textured objects and scene element interactions are realistically rendered by our method, despite having a rough representation as an input. Moreover, our approach allows controllable rendering: geometric and appearance modifications in the input are accurately propagated to the output. The user can move, rotate and scale an object, change its appearance and texture or modify the position of the light and all these edits are represented in the final rendering. We demonstrate the effectiveness of our approach by rendering scenes with varying appearance, from single color per object to complex, high-frequency textures. We show that our rerendering network can generate very detailed images that represent precisely the appearance of the input scene. Our experiments illustrate that our approach achieves more accurate image synthesis results compared to alternatives and can also handle low voxel grid resolutions. Finally, we show how our neural rendering framework can capture and faithfully render objects from real images and from a diverse set of classes.

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。

↑