High Fidelity 3D Reconstructions with Limited Physical Views
This addresses the need for costly multi-view setups in applications requiring high fidelity 3D reconstructions, offering a more practical and accessible solution.
The paper tackles the problem of achieving high fidelity 3D reconstructions with limited camera views, showing that their method can achieve comparable fidelity to expensive multi-view rigs using only 2-3 uncalibrated views.
Multi-view triangulation is the gold standard for 3D reconstruction from 2D correspondences given known calibration and sufficient views. However in practice, expensive multi-view setups -- involving tens sometimes hundreds of cameras -- are required in order to obtain the high fidelity 3D reconstructions necessary for many modern applications. In this paper we present a novel approach that leverages recent advances in 2D-3D lifting using neural shape priors while also enforcing multi-view equivariance. We show how our method can achieve comparable fidelity to expensive calibrated multi-view rigs using a limited (2-3) number of uncalibrated camera views.