SupeRVol: Super-Resolution Shape and Reflectance Estimation in Inverse Volume Rendering
This addresses the problem of high-quality 3D modeling from low-resolution imagery for applications in computer vision and graphics.
The paper tackles the problem of recovering 3D shape and material parameters from color images by proposing SupeRVol, an end-to-end inverse rendering pipeline that uses neural representations and a differentiable volume renderer with a physical illumination model. The method achieves state-of-the-art performance, generating reconstructions sharper than the input images.
We propose an end-to-end inverse rendering pipeline called SupeRVol that allows us to recover 3D shape and material parameters from a set of color images in a super-resolution manner. To this end, we represent both the bidirectional reflectance distribution function (BRDF) and the signed distance function (SDF) by multi-layer perceptrons. In order to obtain both the surface shape and its reflectance properties, we revert to a differentiable volume renderer with a physically based illumination model that allows us to decouple reflectance and lighting. This physical model takes into account the effect of the camera's point spread function thereby enabling a reconstruction of shape and material in a super-resolution quality. Experimental validation confirms that SupeRVol achieves state of the art performance in terms of inverse rendering quality. It generates reconstructions that are sharper than the individual input images, making this method ideally suited for 3D modeling from low-resolution imagery.