AI RESEARCH
OAHuman: Occlusion-Aware 3D Human Reconstruction from Monocular Images
arXiv CS.CV
•
ArXi:2603.14249v1 Announce Type: new Monocular 3D human reconstruction in real-world scenarios remains highly challenging due to frequent occlusions from surrounding objects, people, or image truncation. Such occlusions lead to missing geometry and unreliable appearance cues, severely degrading the completeness and realism of reconstructed human models. Although recent neural implicit methods achieve impressive results on clean inputs, they struggle under occlusion due to entangled modeling of shape and texture.