Research map / 3D vision / Human pose estimation
Refining 3D Human Texture Estimation From a Single Image
Said Fahri Altindis, Adil Meric, Yusuf Dalva, Uğur Güdükbay, Ayşegül Dündar
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add deformable convolution refinement module (ablation) | Texformer-style baseline · Market-1501 | LPIPS (same view): 0.1154 -> 0.1038 | Improved |
| add deformable convolution refinement module (ablation) | baseline · Market-1501 | CosSim (novel view): 0.4943 -> 0.4976 | Improved |
| replace deformable refinement by plain convolutional refinement (ablation) | baseline · Market-1501 | SSIM (same view): 0.7422 -> 0.7196 | Hurt |
| deformable instead of conv refinement (ablation) | baseline · Market-1501 | SSIM (same view): 0.7196 -> 0.7490 | Improved |
| add uncertainty-based reconstruction loss (ablation) | baseline · Market-1501 | SSIM (same view): 0.7422 -> 0.7560 | Improved |
| add uncertainty-based reconstruction loss (ablation) | baseline · Market-1501 | LPIPS (same view): 0.1154 -> 0.1053 | Improved |
| add uncertainty-based reconstruction loss (ablation) | baseline · Market-1501 | CosSim (novel view): 0.4943 -> 0.4802 | Hurt |
| add cycle consistency loss (ablation) | baseline · Market-1501 | LPIPS (same view): 0.1154 -> 0.1107 | Improved |
| add cycle consistency loss (ablation) | baseline · Market-1501 | CosSim (novel view): 0.4943 -> 0.4968 | Improved |
| train with multi-view consistency instead of single-view images (ablation) | baseline · Market-1501 | SSIM (novel view): 0.6494 -> 0.6535 | Improved |
| train with multi-view consistency instead of single-view images (ablation) | baseline · Market-1501 | SSIM (same view): 0.7706 -> 0.7422 | Hurt |
| full method instead of Texformer | Texformer · Market-1501 | SSIM (same view): 0.7422 -> 0.7611 | Improved |
Closest papers by meaning
- 3D Human Texture Estimation From a Single Image With Transformers (ICCV 2021 · similarity 0.90)
- TexturePose: Supervising Human Mesh Estimation With Texture Consistency (ICCV 2019 · similarity 0.90)
- Learning to Estimate 3D Human Pose and Shape From a Single Color Image (CVPR 2018 · similarity 0.89)
- Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures (CVPR 2025 · similarity 0.88)
- SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion (CVPR 2024 · similarity 0.87)
- MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction (CVPR 2025 · similarity 0.87)
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.
