Research map / 3D vision / Face and shape
High-Fidelity 3D Human Digitization From Single 2K Resolution Images
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use 2K2K instead of ICON | single-image human reconstruction · RenderPeople | Normal (radian): 3.78 -> 3.64 | Helped |
| Use 2K2K instead of ICON | single-image human reconstruction · THuman2.0 | Normal (radian): 6.65 -> 5.71 | Helped |
| Use 2K2K instead of ICON | single-image human reconstruction · RenderPeople | P2S (cm): 0.55 -> 1.12 | Hurt |
| Use 2K2K instead of ICON | single-image human reconstruction · THuman2.0 | IoU: 74.6 -> 69.0 | Hurt |
| Increase input resolution from 512×512 to 2048×2048 (ablation) | 2K2K · RenderPeople test | Normal (radian): 4.72 -> 3.69 | Helped |
| Increase input resolution from 512×512 to 2048×2048 (ablation) | 2K2K · RenderPeople test | P2S (cm): 1.17 -> 0.96 | Helped |
| Train with more scan models, from 250 to 2,000 (ablation) | 2K2K · held-out test set | Normal (radian): 7.00 -> 3.65 | Helped |
| Train with more scan models, from 250 to 2,000 (ablation) | 2K2K · held-out test set | P2S (cm): 1.44 -> 0.965 | Helped |
| Train with more scan models, from 250 to 2,000 (ablation) | 2K2K · held-out test set | Chamfer (cm): 1.35 -> 1.010 | Helped |
Closest papers by meaning
- GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data (NeurIPS 2025 · similarity 0.87)
- SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction (NeurIPS 2025 · similarity 0.86)
- Reconstructing Humans with a Biomechanically Accurate Skeleton (CVPR 2025 · similarity 0.86)
- PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing (CVPR 2025 · similarity 0.86)
- MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction (CVPR 2025 · similarity 0.86)
- Joint2Human: High-Quality 3D Human Generation via Compact Spherical Embedding of 3D Joints (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.