SDF-based differential rendering frameworks have achieved state-of-the-art multiview 3D shape reconstruction. In this work, we re-examine this family of approaches by minimally reformulating its core appearance model in a way that simultaneously yields faster computation and increased performance. To this goal, we exhibit a physically-inspired minimal radiance parametrization decoupling angular and spatial contributions, by encoding them with a small number of features stored in two respective volumetric grids of different resolutions. Requiring as little as four parameters per voxel, and a tiny MLP call inside a single fully fused kernel, our approach allows to enhance performance with both surface and image (PSNR) metrics, while providing a significant training speedup and real-time rendering. We show this performance to be consistently achieved on real data over two widely different and popular application fields, generic object and human subject shape reconstruction, using four representative and challenging datasets.

翻译：基于SDF的微分渲染框架已实现最先进的多视角三维形状重建。在本工作中，我们通过对其核心外观模型进行最小化重构，重新审视了此类方法，这种重构方式同时实现了更快的计算速度与更高的性能。为此，我们提出一种受物理启发的极小辐射度参数化方案，将角度贡献与空间贡献解耦，并通过存储在两个不同分辨率体素网格中的少量特征对它们进行编码。我们的方法每个体素仅需四个参数，并在单个完全融合的内核中调用微型MLP，从而能够在表面和图像（PSNR）指标上提升性能，同时实现显著的训练加速和实时渲染能力。我们在真实数据上证明了该性能在两种差异巨大且广泛应用的领域——通用物体与人体主体形状重建——中均能稳定实现，并使用了四个具有代表性且富有挑战性的数据集进行验证。