SMPL Normal Map Is All You Need for Single-view Textured Human Reconstruction
This addresses the problem of reconstructing clothed 3D humans from monocular images for applications in computer vision and graphics, representing an incremental improvement over existing approaches.
The paper tackles single-view textured human reconstruction by proposing the SEHR framework, which integrates SMPL normal maps to improve guidance and constraints, resulting in outperforming state-of-the-art methods on benchmark datasets.
Single-view textured human reconstruction aims to reconstruct a clothed 3D digital human by inputting a monocular 2D image. Existing approaches include feed-forward methods, limited by scarce 3D human data, and diffusion-based methods, prone to erroneous 2D hallucinations. To address these issues, we propose a novel SMPL normal map Equipped 3D Human Reconstruction (SEHR) framework, integrating a pretrained large 3D reconstruction model with human geometry prior. SEHR performs single-view human reconstruction without using a preset diffusion model in one forward propagation. Concretely, SEHR consists of two key components: SMPL Normal Map Guidance (SNMG) and SMPL Normal Map Constraint (SNMC). SNMG incorporates SMPL normal maps into an auxiliary network to provide improved body shape guidance. SNMC enhances invisible body parts by constraining the model to predict an extra SMPL normal Gaussians. Extensive experiments on two benchmark datasets demonstrate that SEHR outperforms existing state-of-the-art methods.