Reconstructing Hand-Held Objects in 3D

arXiv:2404.06507v1 Announce Type: new
Abstract: Objects manipulated by the hand (i.e., manipulanda) are particularly challenging to reconstruct from in-the-wild RGB images or videos. Not only does the hand occlude much of the object, but also the object is often only visible in a small number of image pixels. At the same time, two strong anchors emerge in this setting: (1) estimated 3D hands help disambiguate the location and scale of the object, and (2) the set of manipulanda is small …

abstract anchors arxiv cs.cv image images object objects pixels small type videos