Author name: Jiatong Xia, Zicheng Duan, Anton van den Hengel, Lingqiao Liu

arXiv:2603.18782v3 Announce Type: replace
Abstract: Recent progress in 3D generation has been driven largely by models conditioned on images or text, while readily available 3D priors are still underused. In many real-world scenarios, the visible-regi…