SuperPrimitive: Scene Reconstruction at a Primitive Level

arXiv:2312.05889v2 Announce Type: replace
Abstract: Joint camera pose and dense geometry estimation from a set of images or a monocular video remains a challenging problem due to its computational complexity and inherent visual ambiguities. Most dense incremental reconstruction systems operate directly on image pixels and solve for their 3D positions using multi-view geometry cues. Such pixel-level approaches suffer from ambiguities or violations of multi-view consistency (e.g. caused by textureless or specular surfaces).
We address this issue with a new image …

abstract arxiv complexity computational cs.cv geometry image images incremental pixels set solve systems type video view visual