Neural signed distance functions (SDFs) are emerging as an effective representation for 3D shapes. State-of-the-art methods typically encode the SDF with a large, fixed-size neural network to approximate complex shapes with implicit surfaces. Rendering with these large networks is, however, computationally expensive since it requires many forward passes through the network for every pixel, making these representations impractical for real-time graphics. We introduce an efficient neural representation that, for the first time, enables real-time rendering of high-fidelity neural SDFs, while achieving state-of-the-art geometry reconstruction quality. We represent implicit surfaces using an octree-based feature volume which adaptively fits shapes with multiple discrete levels of detail (LODs), and enables continuous LOD with SDF interpolation. We further develop an efficient algorithm to directly render our novel neural SDF representation in real-time by querying only the necessary LODs with sparse octree traversal. We show that our representation is 2-3 orders of magnitude more efficient in terms of rendering speed compared to previous works. Furthermore, it produces state-of-the-art reconstruction quality for complex shapes under both 3D geometric and 2D image-space metrics.

中文翻译：

---

神经几何细节水平：隐式3D形状的实时渲染

神经符号距离函数（SDF）逐渐成为3D形状的有效表示形式。最先进的方法通常使用固定大小的大型神经网络对SDF进行编码，以近似显示具有隐式表面的复杂形状。然而，由于这些大型网络的渲染在计算上是昂贵的，因为它需要每个像素通过网络进行许多前向传递，这使得这些表示对于实时图形来说是不切实际的。我们引入了一种有效的神经表示，这首次实现了高保真神经SDF的实时渲染，同时实现了最新的几何重构质量。我们使用基于八叉树的特征量表示隐式曲面，该特征量自适应地拟合具有多个离散细节水平（LOD）的形状，并通过SDF插值实现连续的LOD。通过进一步查询稀疏八叉树遍历所需的LOD，我们进一步开发了一种有效的算法，可以直接实时实时呈现新的神经SDF表示。我们表明，与以前的作品相比，在渲染速度方面，我们的表示效率提高了2-3个数量级。此外，它可以在3D几何和2D图像空间指标下为复杂形状提供最新的重建质量。