Neural reflectance models are capable of accurately reproducing the spatially-varying appearance of many real-world materials at different scales. However, existing methods have difficulties handling highly glossy materials. To address this problem, we introduce a new neural reflectance model which, compared with existing methods, better preserves not only specular highlights but also fine-grained details. To this end, we enhance the neural network performance by encoding input data to frequency space, inspired by NeRF, to better preserve the details. Furthermore, we introduce a gradient-based loss and employ it in multiple stages, adaptive to the progress of the learning phase. Lastly, we utilize an optional extension to the decoder network using the Inception module for more accurate yet costly performance. We demonstrate the effectiveness of our method using a variety of synthetic and real examples.

翻译：神经反射模型能够精确复现多种真实材料在不同尺度下的空间变化外观。然而，现有方法在处理高光泽材料时存在困难。针对这一问题，我们提出了一种新型神经反射模型，与现有方法相比，该模型不仅能更好地保留镜面高光，还能保持精细细节。为此，我们受NeRF启发，通过对输入数据进行频域编码来增强神经网络性能，从而更好地保留细节特征。此外，我们引入基于梯度的损失函数，并在多个阶段采用自适应学习进度的策略。最后，我们利用Inception模块对解码器网络进行可选的扩展扩展，以提升精度，尽管这会增加计算成本。通过多种合成与真实样本，我们验证了该方法有效性。