Wild2Avatar: Rendering Humans Behind Occlusions

TL;DR

Wild2Avatar is a neural rendering method designed to generate realistic images of humans in occluded, real-world scenes from monocular videos by decoupling occlusion, human, and background components.

Contribution

The paper introduces occlusion-aware scene parameterization and objective functions for decoupling and complete human modeling in in-the-wild monocular videos.

Findings

Effective rendering of occluded humans in real-world scenes

Decoupling scene components improves rendering quality

Validated on in-the-wild video datasets

Abstract

Rendering the visual appearance of moving humans from occluded monocular videos is a challenging task. Most existing research renders 3D humans under ideal conditions, requiring a clear and unobstructed scene. Those methods cannot be used to render humans in real-world scenes where obstacles may block the camera's view and lead to partial occlusions. In this work, we present Wild2Avatar, a neural rendering approach catered for occluded in-the-wild monocular videos. We propose occlusion-aware scene parameterization for decoupling the scene into three parts - occlusion, human, and background. Additionally, extensive objective functions are designed to help enforce the decoupling of the human from both the occlusion and the background and to ensure the completeness of the human model. We verify the effectiveness of our approach with experiments on in-the-wild videos.