2023/12/06 by Kira Prabhu, Jane Y. Wu, Prabhu, Kira +11 · 4 citations
Computer Science · #Advanced Vision and Imaging #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis
paper · pdf · doi:10.48550/arxiv.2312.03869
openalex publication_date 2023/12/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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 (e.g. a NeRF). Unlike 3D generative methods that explicitly condition the diffusion model on camera pose or multi-view information, our diffusion model is conditioned only on a single masked 2D image. Nevertheless, we show that this 2D diffusion model can still serve as a generative prior in a 3D multi-view reconstruction problem where we optimize a NeRF using a combination of score distillation sampling and NeRF reconstruction losses. Predicted depth is used as additional supervision to encourage accurate geometry. We compare our approach to 3D inpainting methods that focus on object removal. Because our method can generate content to fill any 3D masked region, we additionally demonstrate 3D object completion, 3D object replacement, and 3D scene completion.