PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
October 15, 20250 citationsOpen Access

SMPL Normal Map Is All You Need for Single-view Textured Human Reconstruction

View Full Paper
WSWenhao ShenGZGangjian ZhangJZJianfeng Zhang

Key Points

  • SEHR significantly improves single-view textured human reconstruction from a monocular image.
  • The framework integrates SMPL normal maps for better guidance and enhanced body part prediction.
  • Extensive tests show SEHR outperforms current state-of-the-art reconstruction methods.
  • The method addresses issues of 2D hallucinations and limited 3D data constraints.

Abstract

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.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Shen et al. (2025) studied this question.

synapsesocial.com/papers/68efa18f9d05deea71d13c9ahttps://doi.org/10.48550/arxiv.2506.12793
Ask AI
Helpful
Bookmark
Share
View Full Paper

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1DenseSMPLify: 3D Human Body Parametric Reconstruction Using Pixel Aligned Dense Normal Maps2026
  2. 2Implicit 3D Human Reconstruction Guided by Parametric Models and Normal Maps2024 · 2 citations
  3. 3A FLEXIBLE MULTI-VIEW HUMAN MESH RECONSTRUCTION FRAMEWORK FOR PREDICTING METRIC SMPL PARAMETERS UTILIZING EXISTING SINGLE-VIEW MODELS AS BASE MODELS2026 · 1 citations
  4. 4Semantic Human Mesh Reconstruction with Textures2024
  5. 5PMDI: Combining Parametric-Model and Depth-Aware Implicit Function for Single-View Human Reconstruction2024