Abstract

In this paper, we show how to harness both low-rank and sparse structures in regular or near regular textures for image comple- tion. Our method leverages the new convex optimization for low-rank and sparse signal recovery and can automatically correctly repair the global structure of a corrupted texture, even without precise informa- tion about the regions to be completed. Through extensive simulations, we show our method can complete and repair textures corrupted by er- rors with both random and contiguous supports better than existing low-rank matrix recovery methods. Through experimental comparisons with existing image completion systems (such as Photoshop) our method demonstrate significant advantage over local patch based texture synthe- sis techniques in dealing with large corruption, non-uniform texture, and large perspective deformation.