Can I read No Shadow Left Behind: Removing Objects and their Shadows using Approximate Lighting and Geometry on EtoBox?

No Shadow Left Behind: Removing Objects and their Shadows using Approximate Lighting and Geometry by Zhang, Edward; Martin-Brualla, Ricardo; Kontkanen, Janne; Curless, Brian is a scholarly article available to read on EtoBox.

What is No Shadow Left Behind: Removing Objects and their Shadows using Approximate Lighting and Geometry about?

Removing objects from images is a challenging problem that is important for many applications, including mixed reality. For believable results, the shadows that the object casts should also be removed. Current inpainting-based methods only remove the object itself, leaving shadows behind, or at best require specifying shadow regions to inpaint. We introduce a deep learning pipeline for removing a shadow along with its caster. We leverage rough scene models in order to remove a wide variety of shadows (hard or soft, dark or subtle, large or thin) from surfaces with a wide variety of textures. We train our pipeline on synthetically rendered data, and show qualitative and quantitative results on both synthetic and real scenes.

Author

Zhang, Edward; Martin-Brualla, Ricardo; Kontkanen, Janne; Curless, Brian

Published

2020

Language

EN