Showing 2023Show all
2 papers · 1 filter
cs.CV2023
Inpaint3D: 3D Scene Content Generation using 2D Inpainting Diffusion
Kira Prabhu, Jane Wu, Lynn Tsai +4
This paper presents a novel approach to inpainting 3D regions of a scene, given masked multi-view images, by distilling a 2D diffusion model into a learned 3D scene representation…
cs.CV2023
Readout Guidance: Learning Control from Diffusion Features
Grace Luo, Trevor Darrell, Oliver Wang +2
We present Readout Guidance, a method for controlling text-to-image diffusion models with learned signals. Readout Guidance uses readout heads, lightweight networks trained to extr…