CVGRLGOct 12, 2020

Cut-and-Paste Object Insertion by Enabling Deep Image Prior for Reshading

arXiv:2010.05907v216 citations
AI Analysis

This addresses a challenging issue in image editing for applications like graphics and photography, though it is incremental as it builds on deep image prior techniques.

The paper tackles the problem of realistically inserting objects from one image into another when shading inconsistencies occur, by introducing a method that corrects shading without requiring geometric or material models, and it significantly outperforms baselines in quantitative evaluations and user studies.

We show how to insert an object from one image to another and get realistic results in the hard case, where the shading of the inserted object clashes with the shading of the scene. Rendering objects using an illumination model of the scene doesn't work, because doing so requires a geometric and material model of the object, which is hard to recover from a single image. In this paper, we introduce a method that corrects shading inconsistencies of the inserted object without requiring a geometric and physical model or an environment map. Our method uses a deep image prior (DIP), trained to produce reshaded renderings of inserted objects via consistent image decomposition inferential losses. The resulting image from DIP aims to have (a) an albedo similar to the cut-and-paste albedo, (b) a similar shading field to that of the target scene, and (c) a shading that is consistent with the cut-and-paste surface normals. The result is a simple procedure that produces convincing shading of the inserted object. We show the efficacy of our method both qualitatively and quantitatively for several objects with complex surface properties and also on a dataset of spherical lampshades for quantitative evaluation. Our method significantly outperforms an Image Harmonization (IH) baseline for all these objects. They also outperform the cut-and-paste and IH baselines in a user study with over 100 users.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes