Research map / 3D vision / Face and shape
Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction
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 Front2Back instead of the strongest reported baseline | ShapeNet Core single-view reconstruction · ShapeNet Core test, 13-category mean | MD: 0.0160 -> 0.0144 | Helped |
| Use Front2Back instead of the strongest reported baseline | ShapeNet Core single-view reconstruction · ShapeNet Core test, 13-category mean | Chamfer-L1: 0.0221 -> 0.0206 | Helped |
| Use Front2Back instead of the strongest reported baseline | ShapeNet Core single-view reconstruction · ShapeNet Core test, 13-category mean | Normal Consistency: 0.746 -> 0.759 | Helped |
| Add reflected maps to surface reconstruction (ablation) | Front2Back · Airplanes | MD: 0.0132 -> 0.0129 | Helped |
| Add reflected maps to back-view prediction (ablation) | Front2Back back predictor · Airplanes | Depth avg L1: 0.000593 -> 0.000578 | Helped |
| Add reflected maps to back-view prediction (ablation) | Front2Back back predictor · Airplanes | Normal avg 1-cosine distance: 0.00310 -> 0.00268 | Helped |
| Increase image and map resolution from 137×137 to 256×256 (ablation) | Front2Back · Chairs | MD: 0.013 -> 0.011 | Helped |
| Increase image and map resolution from 137×137 to 256×256 (ablation) | Front2Back · Planes | MD: 0.013 -> 0.011 | Helped |
| Increase image and map resolution from 137×137 to 256×256 (ablation) | Front2Back · Chairs | Chamfer-L1: 0.021 -> 0.018 | Helped |
| Increase image and map resolution from 137×137 to 256×256 (ablation) | Front2Back · Planes | Chamfer-L1: 0.017 -> 0.015 | Helped |
Closest papers by meaning
- 3DReflecNet: A Large-Scale Dataset for 3D Reconstruction of Reflective, Transparent, and Low-Texture Objects (CVPR 2026 · similarity 0.91)
- Fostering Generalization in Single-View 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors (CVPR 2021 · similarity 0.91)
- Learning to Reconstruct Shapes from Unseen Classes (NeurIPS 2018 · similarity 0.91)
- Learning View Priors for Single-View 3D Reconstruction (CVPR 2019 · similarity 0.89)
- Learning Partonomic 3D Reconstruction from Image Collections (CVPR 2025 · similarity 0.89)
- UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections (NeurIPS 2024 · 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.