Research map / 3D vision / Face and shape
Self-supervised Single-view 3D Reconstruction via Semantic Consistency
Xueting Li, Sifei Liu, Kihwan Kim, Shalini De Mello, Varun Jampani, Ming-Hsuan Yang, Jan Kautz
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 semantic consistency constraints (L_sv and L_sp) (ablation) | self-supervised mesh reconstruction · CUB-200-2011 keypoint transfer via camera | PCK: 29.0 -> 51.2 | Improved |
| add semantic consistency constraints (L_sv and L_sp) (ablation) | self-supervised mesh reconstruction · CUB-200-2011 keypoint transfer via texture flow | PCK: 32.8 -> 58.2 | Improved |
| add semantic consistency constraints (L_sv and L_sp) (ablation) | self-supervised mesh reconstruction · CUB-200-2011 | mask IoU: 0.744 -> 0.734 | Hurt |
| add texture cycle consistency constraint (ablation) | self-supervised mesh reconstruction · CUB-200-2011 keypoint transfer via texture flow | PCK: 51.0 -> 58.2 | Improved |
| add texture cycle consistency constraint (ablation) | self-supervised mesh reconstruction · CUB-200-2011 keypoint transfer via camera | PCK: 48.5 -> 51.2 | Improved |
| add texture cycle consistency constraint (ablation) | self-supervised mesh reconstruction · CUB-200-2011 | mask IoU: 0.731 -> 0.734 | No clear effect |
| use SCOPS improved by 3D reconstruction instead of original SCOPS (ablation) | self-supervised mesh reconstruction · CUB-200-2011 keypoint transfer via texture flow | PCK: 52.9 -> 58.2 | Improved |
| use SCOPS improved by 3D reconstruction instead of original SCOPS (ablation) | self-supervised mesh reconstruction · CUB-200-2011 keypoint transfer via camera | PCK: 48.7 -> 51.2 | Improved |
| add vertex-based semantic constraint L_sv (ablation) | self-supervised mesh reconstruction · CUB-200-2011 mask IoU and keypoint transfer | mask IoU: 0.6069 -> 0.734 | Improved |
| add probability-based semantic constraint L_sp (ablation) | self-supervised mesh reconstruction · CUB-200-2011 mask IoU and keypoint transfer | keypoint transfer via texture flow: 53.3 -> 58.2 | Improved |
| self-supervised model without keypoints compared to keypoint-supervised CMR | single-view reconstruction · CUB-200-2011 keypoint transfer via texture flow | PCK: 28.5 -> 58.2 | Improved |
| self-supervised model without keypoints compared to keypoint-supervised CMR on cars | single-view reconstruction · PASCAL3D+ car | mesh IoU: 0.64 -> 0.62 | No clear effect |
Closest papers by meaning
- Learning Category-Specific Mesh Reconstruction from Image Collections (ECCV 2018 · similarity 0.92)
- Self-Supervised 3D Mesh Reconstruction From Single Images (CVPR 2021 · similarity 0.91)
- Learning Partonomic 3D Reconstruction from Image Collections (CVPR 2025 · similarity 0.89)
- MESC-3D:Mining Effective Semantic Cues for 3D Reconstruction from a Single Image (CVPR 2025 · similarity 0.89)
- Self-Supervised 3D Human Mesh Recovery from a Single Image with Uncertainty-Aware Learning (AAAI 2024 · similarity 0.89)
- Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space (CVPR 2025 · similarity 0.89)
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.
