Research map / 3D vision / Face and shape
Share with Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency
Tom Monnier, Matthew Fisher, Alexei A. Efros, Mathieu Aubry
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 |
|---|---|---|---|
| remove supervision: learn from raw images only (UNICORN vs DVR with cam+sil) | UNICORN · ShapeNet (13 classes, no ICP) | Chamfer-L1 mean: 0.598 -> 0.403 | Improved |
| UNICORN without any supervision vs multi-view supervised DVR | UNICORN · ShapeNet (13 classes, no ICP) | Chamfer-L1 mean: 0.236 -> 0.403 | Hurt |
| UNICORN vs UCMR on Pascal3D+ Car (no silhouette or prior) | UNICORN · Pascal3D+ Car | Chamfer-L1: 0.172 -> 0.163 | Improved |
| UNICORN vs UCMR on Pascal3D+ Car | UNICORN · Pascal3D+ Car | Mask IoU: 73.7 -> 83.9 | Improved |
| UNICORN vs UCMR on Pascal3D+ Car | UNICORN · Pascal3D+ Car | 3D IoU: 67.3 -> 65.9 | Hurt |
| UNICORN vs SMR on CUB | UNICORN · CUB-200-2011 | Mask IoU: 80.6 -> 71.4 | Hurt |
| UNICORN vs SMR on CUB | UNICORN · CUB-200-2011 | PCK@0.1: 62.2 -> 49.0 | Hurt |
| add neighbor reconstruction loss L_swap (ablation) | UNICORN · ShapeNet | Chamfer-L1 | Improved |
| add progressive conditioning on airplane and car (ablation) | UNICORN · ShapeNet airplane and car | Chamfer-L1 | No clear effect |
| add progressive conditioning on chair and table (ablation) | UNICORN · ShapeNet chair and table | Chamfer-L1 | Improved |
| sample neighbors from 5 viewpoint bins instead of unconstrained (V=1) (ablation) | neighbor reconstruction · qualitative | latent code quality: 1 -> 5 | Improved |
Closest papers by meaning
- Self-supervised Single-view 3D Reconstruction via Semantic Consistency (ECCV 2020 · similarity 0.90)
- Few-Shot Generalization for Single-Image 3D Reconstruction via Priors (ICCV 2019 · similarity 0.90)
- Fostering Generalization in Single-View 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors (CVPR 2021 · similarity 0.89)
- Learning View Priors for Single-View 3D Reconstruction (CVPR 2019 · similarity 0.89)
- CoReNet: Coherent 3D Scene Reconstruction from a Single RGB Image (ECCV 2020 · similarity 0.89)
- Learning Partonomic 3D Reconstruction from Image Collections (CVPR 2025 · similarity 0.88)
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.
