Bayesian Diffusion Models for 3D Shape Reconstruction

arXiv:2403.06973v1 Announce Type: cross
Abstract: We present Bayesian Diffusion Models (BDM), a prediction algorithm that performs effective Bayesian inference by tightly coupling the top-down (prior) information with the bottom-up (data-driven) procedure via joint diffusion processes. We show the effectiveness of BDM on the 3D shape reconstruction task. Compared to prototypical deep learning data-driven approaches trained on paired (supervised) data-labels (e.g. image-point clouds) datasets, our BDM brings in rich prior information from standalone labels (e.g. point clouds) to improve the bottom-up …

abstract algorithm arxiv bayesian bayesian inference cs.cv cs.lg data data-driven deep learning diffusion diffusion models inference information prediction prior processes show type via