来源：《新科学家》
原文刊登日期：2021年10月25日
本文适合2023考生，适合做完型填空的选文
An artificial intelligence algorithm can transform still images into a high-resolution, explorable 3D world, with potential implications for film effects and virtual reality.
有个人工智能算法可以将静止图像转换为高分辨率、可探索的3D世界，对电影效果和虚拟现实具有潜在的影响。
By feeding the neural network a selection of images of a scene and a rough 3D model of the scene created automatically using off-the-shelf software called COLMAP, it is able to accurately visualise what the scene would look like from any viewpoint.
通过向神经网络输入场景图像的选择，以及使用现成的COLMAP软件自动创建的场景的粗略3D模型，该算法能够从任何视角准确地可视化场景。
The neural network, developed by Darius Rückert and colleagues at the University of Erlangen-Nuremberg in Germany, is different to previous systems because it is able to extract physical properties from still images.
该神经网络由德国埃尔兰根-纽伦堡大学的Rückert及其同事开发，与之前的系统不同，因为它能够从静止图像中提取物理属性。
The system could technically create an explorable 3D world from just two images, but it wouldn’t be very accurate. “The more images you have, the better the quality,” says Rückert. “The model cannot create stuff it hasn’t seen.”
从技术上讲，该系统可以仅从两张图像创建一个可探索的3D世界，但它不会非常精确。“你拥有的图片越多，质量就越好，”Rückert说。“模型无法创造出它没有看到的东西。”
Some of the smoothest examples of the generated environments use between 300 and 350 images captured from different angles. Rückert hopes to improve the system by having it simulate how light bounces off objects in the scene to reach the camera, which would mean fewer still images are needed for accurate 3D rendering.
在生成的环境中，一些最流畅的例子使用了从不同角度拍摄的300到350张图像。Rückert希望改进这个系统，让它模拟光线如何从场景中的物体反射到相机上，这意味着精确的3D渲染需要更少的静止图像。
“Until now, creating photorealistic images from 3D reconstructions wasn’t fully automated and always had perceptible flaws,” says Tim Field, founder of New York-based company Abound Labs.
纽约比比皆是Labs公司的创始人蒂姆•菲尔德表示：“直到现在，从3D重建中创建有照片级真实感的图像还不是完全自动化的，而且总是存在明显的缺陷。”
While Field points out the system still requires the input of accurate 3D data, and doesn’t yet work for moving objects, “the rendering quality is unparalleled”, he says. “It’s proof that automated photorealism is possible.”
菲尔德指出，虽然该系统仍然需要输入精确的3D数据，还不能用于移动物体，但“渲染质量是无与伦比的”，他说。“这证明了自动真实感是可能的。”
Field believes the technology will be used for generating visual effects in films and virtual reality. “It’s going to accelerate the already-hot research field of machine learning-based rendering for computer generated imagery,” he says.
菲尔德认为，这项技术将被用于制作电影的视觉效果和虚拟现实。他说：“这将加速已经很热门的基于机器学习的计算机生成图像渲染研究领域。”