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）能以空前的视觉质量实现新视角合成。然而，为渲染逼真图像，NeRF需对每个像素执行数百次深度多层感知器（MLP）评估——这一计算成本极高，即便在强大现代GPU上也无法实现实时渲染。本文提出一种新颖方法，将NeRF蒸馏并烘焙为与大规模并行图形渲染管线完全兼容的高效网格基神经表示。我们通过编码在双层双重重网格上的神经辐射特征表示场景，通过学习射线-曲面交点的可靠区间内的聚合辐射信息，有效克服了三维表面重建中固有的不准确性。为利用邻近像素的局部几何关系，我们采用屏幕空间卷积替代NeRF中的MLP实现高质量外观。最后，通过新颖的多视角蒸馏优化策略进一步提升了整体框架的性能。我们在多个标准数据集上开展的广泛实验证明了本方法的有效性和优越性。