Research map / 3D vision / Face and shape
Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis
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 |
|---|---|---|---|
| Add class-vector input to the 3D-EPN (ablation) | 3D-EPN · ShapeNet synthetic test set | ℓ1-Err (1283): 2.63** -> 2.48** | Helped |
| Add skip connections to the 3D-EPN (ablation) | 3D-EPN · ShapeNet synthetic test set | ℓ1-Err (1283): 2.63** -> 2.29** | Helped |
| Add both class-vector input and skip connections (ablation) | 3D-EPN · ShapeNet synthetic test set | ℓ1-Err (1283): 2.63** -> 2.29** | Helped |
| Add class-vector input to the 3D-EPN with skip connections (ablation) | 3D-EPN with skip connections · ShapeNet synthetic test set | ℓ1-Err (1283): 2.29** -> 2.29** | No clear effect |
| Add shape synthesis to the 3D-EPN (ablation) | 3D-EPN · ShapeNet synthetic test set | ℓ1-Err (1283): 2.63** -> 2.33 | Helped |
| Add class-vector input and shape synthesis (ablation) | 3D-EPN · ShapeNet synthetic test set | ℓ1-Err (1283): 2.48** -> 2.16 | Helped |
| Add skip connections and shape synthesis (ablation) | 3D-EPN · ShapeNet synthetic test set | ℓ1-Err (1283): 2.29** -> 1.91 | Helped |
| Use shape synthesis without the 3D-EPN (ablation) | Shape completion pipeline · ShapeNet synthetic test set | ℓ1-Err (1283): 1.89 -> 6.92 | Hurt |
| Complete partial input with 3D-EPN before classification | 3D-CNN classification · ShapeNet partial-input test | classification accuracy: 90.9% -> 92.6% | Helped |
| Complete partial input with 3D-EPN before retrieval | 3D-CNN shape retrieval · ShapeNet partial-input test | shape retrieval accuracy: 90.3% -> 95.4% | Helped |
Closest papers by meaning
- ShapeFormer: Transformer-Based Shape Completion via Sparse Representation (CVPR 2022 · similarity 0.90)
- SurfNet: Generating 3D Shape Surfaces Using Deep Residual Networks (CVPR 2017 · similarity 0.90)
- Learning 3D Shape Completion From Laser Scan Data With Weak Supervision (CVPR 2018 · similarity 0.89)
- Unsupervised 3D Shape Completion Through GAN Inversion (CVPR 2021 · similarity 0.89)
- Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion (CVPR 2020 · similarity 0.89)
- RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completion (NeurIPS 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.