ROSSINI: Reconstructing 3D structure from single images: a perceptual reconstruction approach

消费者在电影、电视和虚拟现实（VR）中享受3D内容的沉浸式体验，但制作成本高昂。拍摄3D电影需要两台摄像机来模拟观众的两只眼睛。一个常见但昂贵的替代方案是拍摄单一视图，然后在后期制作中使用视频艺术家创建左眼和右眼的视图。如果计算机可以从2D内容自动生成3D模型（和双目图像）：“将图像提升到3D”，那会怎么样？这是本项目的首要目标。提升到3D有多种用途，例如机器人的路线规划，自动驾驶车辆的避障，以及VR和电影中的应用。从2D图像中估计3D结构是困难的，因为原则上，图像可以从无限多的3D场景中创建。识别这些可能的世界中哪一个是正确的是非常困难的，但人类一直将2D图像解释为3D场景。每当我们看照片、看电视或凝视远方时，我们都会这样做，因为双眼的深度线索很弱。虽然我们在判断距离时会犯一些错误，但我们快速理解任何场景布局的能力使我们能够在任何环境中导航并与之交互。计算机科学家已经建立了机器视觉系统，通过结合场景约束来提升到3D。一种流行的技术是用一组2D图像和相关的3D范围数据来训练深度神经网络。然而，要取得成功，这种方法需要非常大的数据集，这可能是昂贵的获取。此外，性能只有在数据集完整的情况下才会好：如果系统遇到不符合训练数据集的场景或几何体类型，它将失败。大多数方法都是针对特定情况（例如室内或街道场景）进行训练的，这些系统通常对农村场景不太有效，并且不如人类灵活和健壮。最后，这样的系统提供了一个单一的重建输出，没有任何测量的不确定性。用户必须假设三维重建是正确的，这在许多情况下是一个昂贵的假设。计算机系统的设计和评估是基于它们相对于真实的世界的准确性。然而，提升到3D的最终目标并不是完美的精度-而是提供一个3D表示，为人类观察者提供有用和引人注目的视觉体验，或者引导机器人同时避开障碍物。重要的是，人类擅长与3D环境进行交互，即使我们的感知可能会大大偏离真实的度量深度。这表明，在任何和所有环境中，类似人类的表示都是可以实现的，也是足够的。ROSSINI将开发一种新的机器视觉系统，用于3D重建，比以前的方法更灵活，更强大。专注于静态图像，我们将识别对人类重要的关键结构特征。我们将联合收割机神经网络与计算机视觉方法相结合，形成类似人类的场景描述和3D场景模型。我们的目标是（i）产生3D表示，看起来正确的人，即使他们不是严格的几何正确的（ii）这样做的所有类型的场景和（iii）表示在每个重建固有的不确定性。为此，我们将收集人类对图像的解读数据，并将这些信息纳入我们的网络。我们的新训练方法将从人类和现有的地面实况数据集学习;训练算法选择最有用的人类任务（即判断特定图像的深度）以最大限度地提高学习效果。重要的是，包含人类感知数据应该减少所需的训练数据的总量，同时减轻过度依赖特定数据集的风险。此外，经过充分训练后，我们的系统将生成3D重建以及有关深度估计可靠性的信息。

Consumers enjoy the immersive experience of 3D content in cinema, TV and virtual reality (VR), but it is expensive to produce. Filming a 3D movie requires two cameras to simulate the two eyes of the viewer. A common but expensive alternative is to film a single view, then use video artists to create the left and right eyes' views in post-production. What if a computer could automatically produce a 3D model (and binocular images) from 2D content: 'lifting images into 3D'? This is the overarching aim of this project. Lifting into 3D has multiple uses, such as route planning for robots, obstacle avoidance for autonomous vehicles, alongside applications in VR and cinema.Estimating 3D structure from a 2D image is difficult because in principle, the image could have been created from an infinite number of 3D scenes. Identifying which of these possible worlds is correct is very hard, yet humans interpret 2D images as 3D scenes all the time. We do this every time we look at a photograph, watch TV or gaze into the distance, where binocular depth cues are weak. Although we make some errors in judging distances, our ability to quickly understand the layout of any scene enables us to navigate through and interact with any environment.Computer scientists have built machine vision systems for lifting to 3D by incorporating scene constraints. A popular technique is to train a deep neural network with a collection of 2D images and associated 3D range data. However, to be successful, this approach requires a very large dataset, which can be expensive to acquire. Furthermore, performance is only as good as the dataset is complete: if the system encounters a type of scene or geometry that does not conform to the training dataset, it will fail. Most methods have been trained for specific situations - e.g. indoor, or street scenes - and these systems are typically less effective for rural scenes and less flexible and robust than humans. Finally, such systems provide a single reconstructed output, without any measure of uncertainty. The user must assume that the 3D reconstruction is correct, which will be a costly assumption in many cases.Computer systems are designed and evaluated based upon their accuracy with respect to the real world. However, the ultimate goal of lifting into 3D is not perfect accuracy - rather it is to deliver a 3D representation that provides a useful and compelling visual experience for a human observer, or to guide a robot whilst avoiding obstacles. Importantly, humans are expert at interacting with 3D environments, even though our perception can deviate substantially from true metric depth. This suggests that human-like representations are both achievable and sufficient, in any and all environments.ROSSINI will develop a new machine vision system for 3D reconstruction that is more flexible and robust than previous methods. Focussing on static images, we will identify key structural features that are important to humans. We will combine neural networks with computer vision methods to form human-like descriptions of scenes and 3D scene models. Our aims are to (i) produce 3D representations that look correct to humans even if they are not strictly geometrically correct (ii) do so for all types of scene and (iii) express the uncertainty inherent in each reconstruction. To this end we will collect data on human interpretation of images and incorporate this information into our network. Our novel training method will learn from humans and existing ground truth datasets; the training algorithm selecting the most useful human tasks (i.e. judge depth within a particular image) to maximise learning. Importantly, the inclusion of human perceptual data should reduce the overall quantity of training data required, while mitigating the risk of over-reliance on a specific dataset. Moreover, when fully trained, our system will produce 3D reconstructions alongside information about the reliability of the depth estimates.