Physically based rendering (PBR) material estimation is a fundamental appearance decomposition task with broad applications in virtual content creation, relighting, and digital human rendering. However, estimating PBR materials from a single human image remains highly ill-posed, since illumination, geometry, and reflectance are heavily entangled in the observed appearance. To mitigate this ambiguity, we propose HAFMat, a hybrid-prior-guided framework for single-image human material estimation. Our method introduces guidance maps that encode complementary cues, including appearance, body geometry, structure, and prior material predictions from pre-trained models. A key observation is that these guidance cues are heterogeneous: some cues mainly provide texture-level constraints, while others convey higher-level semantic information. To exploit this property, we design a Multi-layer Adaptive Feature Fusion Mechanism, which adaptively fuses guidance features with decoder features at different stages. This design enables texture-dominant and semantic-dominant cues to guide material decoding at appropriate levels, leading to more accurate and physically plausible material estimation. Extensive experiments on both synthetic and real data demonstrate that our method achieves state-of-the-art performance in material estimation and downstream relighting.

翻译：基于物理渲染（PBR）的材质估计是一项基础外观分解任务，在虚拟内容创作、重光照及数字人体渲染中具有广泛应用。然而，从单幅人体图像估计PBR材质仍是一个高度病态问题，因为光照、几何与反射率在观测外观中紧密纠缠。为缓解这种模糊性，我们提出HAFMat——一种混合先导框架，用于单幅图像人体材质估计。本方法引入能编码互补线索的引导图，包括外观、人体几何、结构以及来自预训练模型的先验材质预测。关键发现是：这些引导线索具有异质性——部分线索主要提供纹理级约束，而其他线索传递更高层语义信息。为利用这一特性，我们设计了一种多层自适应特征融合机制，可在不同阶段自适应融合引导特征与解码器特征。该设计使纹理主导线索与语义主导线索能在恰当层级引导材质解码，从而获得更精准且符合物理规律的材质估计。在合成数据与真实数据上的大量实验表明，本方法在材质估计及下游重光照任务中均达到当前最优性能。