Chitnis Shubham, Sole Aditya, Chandran Sharat
ViGIL, Indian Institute of Technology Bombay, Mumbai 400076, India.
Colourlab, Department of Computer Science, Norwegian University of Science and Technology (NTNU), 2815 Gjøvik, Norway.
J Imaging. 2025 Jan 11;11(1):18. doi: 10.3390/jimaging11010018.
Non-diffuse materials (e.g., metallic inks, varnishes, and paints) are widely used in real-world applications. Accurate rendering relies on the bidirectional reflectance distribution function (BRDF). Current methods of capturing the BRDFs have proven to be onerous in accomplishing quick turnaround time, from conception and design to production. We propose a multi-layer perceptron for compact spectral material representations, with 31 wavelengths for four real-world packaging materials. Our neural-based scenario reduces measurement requirements while maintaining significant saliency. Unlike tristimulus BRDF acquisition, this spectral approach has not, to our knowledge, been previously explored with neural networks. We demonstrate compelling results for diffuse, glossy, and goniochromatic materials.
非漫反射材料（如金属油墨、清漆和涂料）在实际应用中广泛使用。精确的渲染依赖于双向反射分布函数（BRDF）。目前获取BRDF的方法在实现从概念设计到生产的快速周转时间方面已被证明很繁琐。我们提出了一种用于紧凑光谱材料表示的多层感知器，针对四种实际包装材料采用31个波长。我们基于神经网络的方案在保持显著显著性的同时减少了测量要求。与三刺激值BRDF采集不同，据我们所知，这种光谱方法以前尚未用神经网络进行过探索。我们展示了对于漫反射、光泽和变色材料的令人信服的结果。
