From Phase to Phenomenon: Self-Supervised Learning of Subsurface Scattering with Minimal Phase-shift Inputs

We propose a self-supervised pretraining framework for learn-ing sub-surface scattering (SSS) light transport representations fromminimal input. Our method leverages a stereo projector–camera setupthat captures only eight high-frequency phase-shift profilometry (PSP)images per view to pretrain an encoder in a multi-view, multi-object set-ting. We introduce a tailored augmentation strategy for PSP-based SSSdata, and show that it significantly outperforms standard ImageNet-styleaugmentations for SSL pretraining. The pretrained encoder learns gen-eralizable SSS representations that transfer effectively to downstreamtasks, including spatially varying relighting and representation evalua-tion using a kNN classifier. Combined with a decoder, the model recon-structs dense scattering footprint responses, trained using a dedicatedcost function that improves accuracy, particularly for anisotropic foot-prints. An overview of our method is presented in Fig. 3. Despite usingonly eight input images per view, our approach generalizes to unseenobjects with complex geometry and material properties, achieving high-fidelity reconstructions while requiring orders of magnitude fewer imagesthan prior methods. Our code is publicly available at GitHub.