Severalworksextend thesetodynamic scenes captured with monocular video, with promising performance.

While 3D Gaussians efficiently approximate an object's surface, they fail to capture the volumetric properties of subsurface scattering. We propose a framework for optimizing an object's shape together with the radiance transfer field given multi-view OLA T (one light at a time) data.

However error control for inverse graphics is difficult, and inverse graphics methods can represent only the effects of the chosen intrinsics.

We introduce Stanford-ORB, a new real-world 3D Object inverse Rendering Benchmark.

We introduce OpenIllumination, a real-world dataset containing over 108K images of 64 objects with diverse materials, captured under 72 camera views and a large number of different illuminations. For each image in the dataset, we provide accurate camera parameters, illumination ground truth, and foreground segmentation masks. Our dataset enables the quantitative evaluation of most inverse rendering and material decomposition methods for real objects.

Neural Information Processing Systems http://nips.cc/