G-NeRF: Geometry-enhanced Novel View Synthesis from Single-View Images

arXiv:2404.07474v1 Announce Type: new
Abstract: Novel view synthesis aims to generate new view images of a given view image collection. Recent attempts address this problem relying on 3D geometry priors (e.g., shapes, sizes, and positions) learned from multi-view images. However, such methods encounter the following limitations: 1) they require a set of multi-view images as training data for a specific scene (e.g., face, car or chair), which is often unavailable in many real-world scenarios; 2) they fail to extract the …

abstract arxiv collection cs.cv generate geometry however image images limitations nerf novel set synthesis type view