In this work, we propose an inverse rendering model that estimates 3D shape, spatially-varying reflectance, homogeneous subsurface scattering parameters, and an environment illumination jointly from only a pair of captured images of a translucent object. In order to solve the ambiguity problem of inverse rendering, we use a physically-based renderer and a neural renderer for scene reconstruction and material editing. Because two renderers are differentiable, we can compute a reconstruction loss to assist parameter estimation. To enhance the supervision of the proposed neural renderer, we also propose an augmented loss. In addition, we use a flash and no-flash image pair as the input. To supervise the training, we constructed a large-scale synthetic dataset of translucent objects, which consists of 117K scenes. Qualitative and quantitative results on both synthetic and real-world datasets demonstrated the effectiveness of the proposed model.

翻译：本文提出一种逆渲染模型，该模型仅通过半透明物体的两幅捕获图像即可联合估计其三维形状、空间变化反射率、均匀次表面散射参数及环境光照。为解决逆渲染中的歧义问题，我们分别采用基于物理的渲染器和神经渲染器进行场景重建与材质编辑。由于两种渲染器均可微，我们可通过计算重建损失来辅助参数估计。为增强所提神经渲染器的监督能力，我们进一步提出一种增广损失函数。此外，我们采用闪光/非闪光图像对作为输入。为监督训练过程，构建了包含11.7万个场景的大规模半透明物体合成数据集。在合成与真实数据集上的定性和定量结果均验证了所提模型的有效性。