We present Intrinsic Image Diffusion, a generative model for appearance
decomposition of indoor scenes. Given a single input view, we sample multiple
possible material explanations represented as albedo, roughness, and metallic
maps. Appearance decomposition poses a considerable challenge in computer
vision due to the inherent ambiguity between lighting and material properties
and the lack of real datasets. To address this issue, we advocate for a
probabilistic formulation, where instead of attempting to directly predict the
true material properties, we employ a conditional generative model to sample
from the solution space. Furthermore, we show that utilizing the strong learned
prior of recent diffusion models trained on large-scale real-world images can
be adapted to material estimation and highly improves the generalization to
real images. Our method produces significantly sharper, more consistent, and
more detailed materials, outperforming state-of-the-art methods by $1.5dB$ on
PSNR and by $45\%$ better FID score on albedo prediction. We demonstrate the
effectiveness of our approach through experiments on both synthetic and
real-world datasets.

使用内在图像扩散，我们提出了一种室内场景外观分解的生成模型。通过给定单个输入视图，我们对多个可能的材质解释进行采样，这些解释由反照率、粗糙度和金属性地图表示。通过引入概率形式来处理外观分解的挑战，我们利用了最近在大规模真实世界图像上训练的强大学习预测器，将其应用于材料估计，并在 PSNR 上超过了现有方法 1.5dB，在反照率预测上 FID 分数提高了 45%。通过在合成和真实世界数据集上进行实验证明了我们方法的有效性。