OAHuman: Occlusion-Aware 3D Human Reconstruction from Monocular Images

TL;DR

OAHuman introduces an occlusion-aware framework that decouples geometry and texture reconstruction, significantly improving the robustness and realism of monocular 3D human models in occluded scenarios.

Contribution

The paper proposes a novel decoupling-perception paradigm that isolates geometry from texture, enhancing reconstruction quality under occlusion.

Findings

Outperforms existing methods on occlusion-rich benchmarks.

Achieves higher structural completeness and surface detail.

Improves texture realism in occluded regions.

Abstract

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. In this paper, we propose OAHuman, an occlusion-aware framework that explicitly decouples geometry reconstruction and texture synthesis for robust 3D human modeling from a single RGB image. The core innovation lies in the decoupling-perception paradigm, which addresses the fundamental issue of geometry-texture cross-contamination in occluded regions. Our framework ensures that geometry reconstruction is perceptually reinforced even in occluded areas, isolating it from texture interference. In parallel, texture synthesis is learned exclusively from visible regions, preventing texture errors from being transferred to the occluded areas. This decoupling approach enables OAHuman to achieve robust and high-fidelity reconstruction under occlusion, which has been a long-standing challenge in the field. Extensive experiments on occlusion-rich benchmarks demonstrate that OAHuman achieves superior performance in terms of structural completeness, surface detail, and texture realism, significantly improving monocular 3D human reconstruction under occlusion conditions.