论文标题
模棱两可的神经渲染
Equivariant Neural Rendering
论文作者
论文摘要
我们提出了一个直接从图像中学习神经场景表示的框架，而无需3D监督。我们的关键见解是，可以通过确保学习的表示形式像真实的3D场景一样施加3D结构。具体而言，我们引入了一种损失，该损失对3D变换实施了场景表示形式。我们的配方使我们能够实时推断和渲染场景，同时获得与需要推断分钟的模型相当的结果。此外，我们介绍了两个挑战性的新数据集用于场景表示和神经渲染，包括具有复杂照明和背景的场景。通过实验，我们表明我们的模型在这些数据集以及标准的塑形基准上实现了令人信服的结果。
We propose a framework for learning neural scene representations directly from images, without 3D supervision. Our key insight is that 3D structure can be imposed by ensuring that the learned representation transforms like a real 3D scene. Specifically, we introduce a loss which enforces equivariance of the scene representation with respect to 3D transformations. Our formulation allows us to infer and render scenes in real time while achieving comparable results to models requiring minutes for inference. In addition, we introduce two challenging new datasets for scene representation and neural rendering, including scenes with complex lighting and backgrounds. Through experiments, we show that our model achieves compelling results on these datasets as well as on standard ShapeNet benchmarks.
