arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2001.04528cs.GRcs.LGeess.IV
收藏

基于深度3D网络的实体纹理按需合成

On Demand Solid Texture Synthesis Using Deep 3D Networks

Polytechnique Montréal(蒙特利尔综合理工学院);Normandie Univ.(诺曼底大学);UniCaen(卡昂大学);ENSICAEN(卡昂高等工程师学院);CNRS(法国国家科学研究中心);GREYC(GREYC实验室);Institut Denis Poisson(德尼·泊松研究所);Université d’Orléans(奥尔良大学);Université de Tours(图尔大学)

Jorge Gutierrez, Julien Rabin, Bruno Galerne, Thomas Hurtut

摘要:

本文介绍了一种新的方法,按需体积纹理合成的基础上的深度学习框架,允许生成高质量的3D数据的交互速率。基于纹理的一些示例图像,训练生成网络来合成任意大小的实体纹理的相干部分,这些相干部分沿着某些方向再现示例的视觉特征。为了应对GPU上的高分辨率和3D处理所固有的内存限制和计算复杂性,在训练阶段仅生成称为“切片”的2D纹理。这些合成纹理通过基于预先训练的深度网络的感知损失函数与示例图像进行比较。所提出的网络非常轻(小于100k参数),因此它只需要可持续的训练(即几个小时),并且能够在单个GPU上非常快速地生成(对于$256^3$体素,大约一秒)。与空间种子PRNG集成,所提出的生成器网络直接返回给定一组3D坐标的RGB值。合成的体积具有良好的视觉效果,至少相当于最先进的基于补丁的方法。它们自然是无缝拼接的,可以完全并行生成。

英文摘要:

This paper describes a novel approach for on demand volumetric texture synthesis based on a deep learning framework that allows for the generation of high quality 3D data at interactive rates. Based on a few example images of textures, a generative network is trained to synthesize coherent portions of solid textures of arbitrary sizes that reproduce the visual characteristics of the examples along some directions. To cope with memory limitations and computation complexity that are inherent to both high resolution and 3D processing on the GPU, only 2D textures referred to as "slices" are generated during the training stage. These synthetic textures are compared to exemplar images via a perceptual loss function based on a pre-trained deep network. The proposed network is very light (less than 100k parameters), therefore it only requires sustainable training (i.e. few hours) and is capable of very fast generation (around a second for $256^3$ voxels) on a single GPU. Integrated with a spatially seeded PRNG the proposed generator network directly returns an RGB value given a set of 3D coordinates. The synthesized volumes have good visual results that are at least equivalent to the state-of-the-art patch based approaches. They are naturally seamlessly tileable and can be fully generated in parallel.

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。

↑