用频域修正提升神经材质建模精度，让电脑渲染更接近真实照片。
FreNBRDF: A Frequency-Rectified Neural Material Representation
- 引入球谐函数与频域损失，优化神经材质表示的频率特性
- 相比现有方法，材质重建与编辑更准确、鲁棒性更强
- 适合需要高保真材质渲染的图形学研究与应用
精确的材质建模对于实现逼真的渲染至关重要，有助于弥合计算机生成图像与真实照片之间的差距。传统方法依赖于表格化的BRDF数据，而近期工作转向隐式神经表示，提供了紧凑且灵活的框架，适用于多种任务。然而，其在频域中的行为仍不清晰。为此，我们提出FreNBRDF，一种频域修正的神经材质表示方法。通过利用球谐函数，将频域考虑融入神经BRDF建模中。我们提出一种新的频域修正损失，基于对神经材质的频域分析，并将其集成到可泛化且自适应的重建与编辑流程中。该框架提升了保真度、适应性和效率。大量实验表明，相较于最先进基线，FreNBRDF在材质外观重建与编辑的准确性与鲁棒性上均有提升，使下游任务更具结构性和可解释性。
原文摘要 · Abstract (English)
Accurate material modeling is crucial for achieving photorealistic rendering, bridging the gap between computer-generated imagery and real-world photographs. While traditional approaches rely on tabulated BRDF data, recent work has shifted towards implicit neural representations, which offer compact and flexible frameworks for a range of tasks. However, their behavior in the frequency domain remains poorly understood. To address this, we introduce FreNBRDF, a frequency-rectified neural material representation. By leveraging spherical harmonics, we integrate frequency-domain considerations into neural BRDF modeling. We propose a novel frequency-rectified loss, derived from a frequency analysis of neural materials, and incorporate it into a generalizable and adaptive reconstruction and editing pipeline. This framework enhances fidelity, adaptability, and efficiency. Extensive experiments demonstrate that FreNBRDF improves the accuracy and robustness of material appearance reconstruction and editing compared to state-of-the-art baselines, enabling more structured and interpretable downstream tasks and applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。