Abstract: Recent advancements in 3D content generation have shown remarkable success by leveraging pretrained large-scale diffusion models. However, existing 3D generation results are far from perfect ...

LoD-Loc tackles visual localization w.r.t a scene represented as LoD 3D map. Given a query image and its pose prior, the method utilizes the wireframe of LoD models to recover the camera pose. This ...

In 3D modeling, designers often use an existing 3D model as a reference to create new ones. This practice has inspired the development of Phidias, a novel generative model that uses diffusion for ...