GeoFill: Reference-Based Image Inpainting with Better Geometric Understanding

arxiv(2023)

引用 0|浏览51
暂无评分
摘要
Reference-guided image inpainting restores image pixels by leveraging the content from another single reference image. The primary challenge is how to precisely place the pixels from the reference image into the hole region. Therefore, understanding the 3D geometry that relates pixels between two views is a crucial step towards building a better model. Given the complexity of handling various types of reference images, we focus on the scenario where the images are captured by freely moving the same camera around. Compared to the previous work, we propose a principled approach that does not make heuristic assumptions about the planarity of the scene. We leverage a monocular depth estimate and predict relative pose between cameras, then align the reference image to the target by a differentiable 3D reprojection and a joint optimization of relative pose and depth map scale and offset. Our approach achieves state-of-the-art performance on both RealEstate10K and MannequinChallenge dataset with large baselines, complex geometry and extreme camera motions. We experimentally verify our approach is also better at handling large holes.
更多
查看译文
关键词
better geometric understanding,image,reference-based
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要