Φeat：基于物理基础的特征表示

摘要

基础模型已成为众多视觉任务的有效骨干网络。然而，当前自监督特征将高层语义与低层物理因素（如几何形状和光照）相互纠缠，阻碍了其在需要显式物理推理任务中的应用。本文提出Φeat——一种新型物理驱动的视觉骨干网络，它能促进对材质标识（包括反射率线索和几何细观结构）敏感的表征能力。我们的核心思路是采用一种预训练策略，通过对比不同形状和光照条件下同一材质的空间裁剪样本与物理增强样本来实现这一目标。虽然类似数据此前已被用于本征分解或材质估计等高阶监督任务，但我们证明纯自监督训练策略无需显式标注即可为需要对外部物理因素具有不变性的鲁棒特征任务提供强先验。我们通过特征相似性分析和材质选择评估所学表征，表明Φeat能捕捉超越语义分组的物理驱动结构。这些发现凸显了无监督物理特征学习作为视觉与图形学领域物理感知基础的前景。

English

Foundation models have emerged as effective backbones for many vision tasks. However, current self-supervised features entangle high-level semantics with low-level physical factors, such as geometry and illumination, hindering their use in tasks requiring explicit physical reasoning. In this paper, we introduce Φeat, a novel physically-grounded visual backbone that encourages a representation sensitive to material identity, including reflectance cues and geometric mesostructure. Our key idea is to employ a pretraining strategy that contrasts spatial crops and physical augmentations of the same material under varying shapes and lighting conditions. While similar data have been used in high-end supervised tasks such as intrinsic decomposition or material estimation, we demonstrate that a pure self-supervised training strategy, without explicit labels, already provides a strong prior for tasks requiring robust features invariant to external physical factors. We evaluate the learned representations through feature similarity analysis and material selection, showing that Φeat captures physically-grounded structure beyond semantic grouping. These findings highlight the promise of unsupervised physical feature learning as a foundation for physics-aware perception in vision and graphics. These findings highlight the promise of unsupervised physical feature learning as a foundation for physics-aware perception in vision and graphics.

Φeat：基于物理基础的特征表示

Φeat: Physically-Grounded Feature Representation

摘要

Support