Neural radiance fields (NeRFs) enable novel view synthesis with unprecedented visual quality. However, to render photorealistic images, NeRFs require hundreds of deep multilayer perceptron (MLP) evaluations - for each pixel. This is prohibitively expensive and makes real-time rendering infeasible, even on powerful modern GPUs. In this paper, we propose a novel approach to distill and bake NeRFs into highly efficient mesh-based neural representations that are fully compatible with the massively parallel graphics rendering pipeline. We represent scenes as neural radiance features encoded on a two-layer duplex mesh, which effectively overcomes the inherent inaccuracies in 3D surface reconstruction by learning the aggregated radiance information from a reliable interval of ray-surface intersections. To exploit local geometric relationships of nearby pixels, we leverage screen-space convolutions instead of the MLPs used in NeRFs to achieve high-quality appearance. Finally, the performance of the whole framework is further boosted by a novel multi-view distillation optimization strategy. We demonstrate the effectiveness and superiority of our approach via extensive experiments on a range of standard datasets.
翻译:神经辐射场(NeRF)可以以前所未有的视觉质量合成新颖视图。然而,为了呈现逼真的图像,NeRF需要为每个像素执行数百次深度多层感知机(MLP)评估。这是非常昂贵的,即使在强大的现代GPU上也无法实现实时渲染。在本文中,我们提出了一种将NeRF精炼和打包成高效的基于网格的神经表示的新方法,这种方法完全兼容于大规模并行图形渲染管线。我们将场景表示为编码在两层双层网格上的神经辐射特征,这有效地通过学习可靠的射线-曲面交点区间中的聚合辐射信息来克服3D表面重建中固有的不准确性。为了利用附近像素的局部几何关系,我们利用屏幕空间卷积代替NeRF中使用的MLP,以实现高质量的外观。最后,整个框架的性能通过一种新颖的多视角蒸馏优化策略进一步提高。我们通过在一系列标准数据集上进行广泛的实验来展示我们方法的有效性和优越性。