TensoIR: Tensorial Inverse Rendering

arXiv:2304.12461v2 Announce Type: replace
Abstract: We propose TensoIR, a novel inverse rendering approach based on tensor factorization and neural fields. Unlike previous works that use purely MLP-based neural fields, thus suffering from low capacity and high computation costs, we extend TensoRF, a state-of-the-art approach for radiance field modeling, to estimate scene geometry, surface reflectance, and environment illumination from multi-view images captured under unknown lighting conditions. Our approach jointly achieves radiance field reconstruction and physically-based model estimation, leading to photo-realistic novel …

abstract art arxiv capacity computation costs cs.cv environment factorization fields geometry inverse rendering low mlp modeling novel rendering scene geometry state surface tensor type