Presentation

· Contributors · Organizations · Search Program

TensoSDF: Roughness-aware Tensorial Representation for Robust Geometry and Material Reconstruction

DescriptionWe propose a novel framework for robust geometry and material reconstruction. The framework's core is the roughness-aware incorporation of the radiance and reflectance fields to reconstruct arbitrary reflective objects. The proposed TensoSDF representation enhances the geometry details while accelerating the training, and the explicit-implicit fusion strategy enables accurate material estimation.

Authors

The Hong Kong Polytechnic University