RealFill: Reference-Driven Generation for Authentic Image Completion

TL;DR

RealFill is a personalized image completion method that uses reference images to generate authentic, scene-faithful content in missing regions, outperforming existing approaches on diverse benchmarks.

Contribution

Introducing RealFill, a novel reference-driven generative model for authentic image completion that handles unaligned, varied reference images to produce scene-faithful results.

Findings

Outperforms existing methods by a large margin on new benchmark

Handles unaligned reference images with varying viewpoints and styles

Produces visually compelling, scene-faithful image completions

Abstract

Recent advances in generative imagery have brought forth outpainting and inpainting models that can produce high-quality, plausible image content in unknown regions. However, the content these models hallucinate is necessarily inauthentic, since they are unaware of the true scene. In this work, we propose RealFill, a novel generative approach for image completion that fills in missing regions of an image with the content that should have been there. RealFill is a generative inpainting model that is personalized using only a few reference images of a scene. These reference images do not have to be aligned with the target image, and can be taken with drastically varying viewpoints, lighting conditions, camera apertures, or image styles. Once personalized, RealFill is able to complete a target image with visually compelling contents that are faithful to the original scene. We evaluate RealFill on a new image completion benchmark that covers a set of diverse and challenging scenarios, and find that it outperforms existing approaches by a large margin. Project page: https://realfill.github.io