2 papers
cs.CV2024
Lightplane: Highly-Scalable Components for Neural 3D Fields
Ang Cao, Justin Johnson, Andrea Vedaldi +1
Contemporary 3D research, particularly in reconstruction and generation, heavily relies on 2D images for inputs or supervision. However, current designs for these 2D-3D mapping are…
cs.CV2024
Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting
Paul Engstler, Andrea Vedaldi, Iro Laina +1
3D scene generation has quickly become a challenging new research direction, fueled by consistent improvements of 2D generative diffusion models. Most prior work in this area gener…