Inpaint3D: 3D Scene Content Generation using 2D Inpainting Diffusion

no code implementations • 6 Dec 2023 • Kira Prabhu, Jane Wu, Lynn Tsai, Peter Hedman, Dan B Goldman, Ben Poole, Michael Broxton

We compare our approach to 3D inpainting methods that focus on object removal.

3D Inpainting Object

Readout Guidance: Learning Control from Diffusion Features

no code implementations • CVPR 2024 • Grace Luo, Trevor Darrell, Oliver Wang, Dan B Goldman, Aleksander Holynski

We present Readout Guidance, a method for controlling text-to-image diffusion models with learned signals.

HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields

2 code implementations • 24 Jun 2021 • Keunhong Park, Utkarsh Sinha, Peter Hedman, Jonathan T. Barron, Sofien Bouaziz, Dan B Goldman, Ricardo Martin-Brualla, Steven M. Seitz

A common approach to reconstruct such non-rigid scenes is through the use of a learned deformation field mapping from coordinates in each input image into a canonical template coordinate space.

Novel View Synthesis

Neural RGB-D Surface Reconstruction

2 code implementations • CVPR 2022 • Dejan Azinović, Ricardo Martin-Brualla, Dan B Goldman, Matthias Nießner, Justus Thies

Obtaining high-quality 3D reconstructions of room-scale scenes is of paramount importance for upcoming applications in AR or VR.

Image Generation Mixed Reality +2

Nerfies: Deformable Neural Radiance Fields

2 code implementations • ICCV 2021 • Keunhong Park, Utkarsh Sinha, Jonathan T. Barron, Sofien Bouaziz, Dan B Goldman, Steven M. Seitz, Ricardo Martin-Brualla

We present the first method capable of photorealistically reconstructing deformable scenes using photos/videos captured casually from mobile phones.

3D Human Reconstruction