Wild2Avatar: Rendering Humans Behind Occlusions
This addresses the challenge of rendering occluded humans in real-world videos for applications like AR/VR, though it appears incremental by adapting neural rendering to occlusion scenarios.
The paper tackles the problem of rendering 3D humans from occluded monocular videos, which existing methods fail to handle, and presents Wild2Avatar, achieving effective rendering in real-world scenes with obstacles.
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.