Research map / 3D vision / Face and shape
Prior Based Human Completion
Check 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 learned structure and texture correlation priors (ablation) | human completion model · LIP | mIoU: 51.96% -> 53.78% | Helped |
| Use learned structure and texture correlation priors (ablation) | human completion model · LIP | PSNR: 20.07 -> 22.99 | Helped |
| Use learned structure and texture correlation priors (ablation) | human completion model · LIP | SSIM: 0.7969 -> 0.8561 | Helped |
| Use multi-scale structure discriminators (ablation) | human completion model · LIP | mIoU: 51.96% -> 53.56% | Helped |
| Use multi-scale structure discriminators (ablation) | human completion model · LIP | PSNR: 20.07 -> 22.63 | Helped |
| Use multi-scale structure discriminators (ablation) | human completion model · LIP | SSIM: 0.7969 -> 0.7819 | Hurt |
| Combine correlation priors and multi-scale structure discriminators (ablation) | human completion model · LIP | mIoU: 51.96% -> 56.22% | Helped |
| Combine correlation priors and multi-scale structure discriminators (ablation) | human completion model · LIP | PSNR: 20.07 -> 25.57 | Helped |
| Combine correlation priors and multi-scale structure discriminators (ablation) | human completion model · LIP | SSIM: 0.7969 -> 0.9139 | Helped |
| Use the proposed completion method instead of DeepFill v2 | human completion model · LIP, vanilla human completion | PSNR: 23.06 -> 25.57 | Helped |
| Use the proposed completion method instead of DeepFill v2 | human completion model · Chictopia10K, vanilla human completion | PSNR: 31.91 -> 36.58 | Helped |
| Condition completion on human structure and use the proposed method | human completion model · LIP, structure-based human completion | mIoU: 37.65% -> 56.22% | Helped |
Closest papers by meaning
- Large Occluded Human Image Completion via Image-Prior Cooperating (AAAI 2024 · similarity 0.89)
- HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation (NeurIPS 2025 · similarity 0.85)
- MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction (CVPR 2025 · similarity 0.85)
- HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors (NeurIPS 2024 · similarity 0.85)
- DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Models (NeurIPS 2026 · similarity 0.84)
- SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion (CVPR 2024 · similarity 0.84)
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.