Abstract: 3D Visual Grounding (3DVG) aims at localizing 3D object based on textual descriptions. Conventional supervised methods for 3DVG often necessitate extensive annotations and a predefined ...
Abstract: Novel-view synthesis, which generates new views from images captured at multiple viewpoints, is widely applied in fields such as autonomous driving, robotic vision, architecture, and ...
2 papers removed: GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions, GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting 4 papers' status updated. Structure ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback