WorDepth: Variational Language Prior for Monocular Depth Estimation

arXiv:2404.03635v1 Announce Type: cross
Abstract: Three-dimensional (3D) reconstruction from a single image is an ill-posed problem with inherent ambiguities, i.e. scale. Predicting a 3D scene from text description(s) is similarly ill-posed, i.e. spatial arrangements of objects described. We investigate the question of whether two inherently ambiguous modalities can be used in conjunction to produce metric-scaled reconstructions. To test this, we focus on monocular depth estimation, the problem of predicting a dense depth map from a single image, but with an …

abstract arxiv cs.ai cs.cl cs.cv cs.lg cs.mm image language objects prior question scale spatial text three-dimensional type