Research map / 3D vision / Face and shape
MLVCNN: Multi-Loop-View Convolutional Neural Network for 3D Shape Retrieval
Read the paperCheck 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 Loop Normalization (ablation) | MLVCNN 3x8 · ModelNet40 retrieval | mAP: 88.55% -> 91.07% | Helped |
| add Loop Normalization (1 loop) (ablation) | MLVCNN · ModelNet40 retrieval | mAP: 84.38% -> 85.89% | Helped |
| use multi-loop views (3 loops vs 1) with 8 views/loop (ablation) | MLVCNN · ModelNet40 retrieval | mAP: 85.89% -> 91.07% | Helped |
| increase views from 8 to 24 | MVCNN · ModelNet40 retrieval | mAP: 80.52% -> 74.96% | Hurt |
| add LSTM sequence modeling over loop views (MLVCNN vs MVCNN, 8 views) (ablation) | MVCNN · ModelNet40 retrieval | mAP: 80.52% -> 85.89% | Helped |
| increase views per loop from 4 to 12 (ablation) | MLVCNN 3 loops · ModelNet40 retrieval | mAP: 88.85% -> 91.15% | Helped |
| add Center Loss (ablation) | MLVCNN 3x12 · ModelNet40 retrieval | mAP: 91.15% -> 92.84% | Helped |
| increase loops from 3 to 6 (ablation) | MLVCNN with LN · ModelNet40 retrieval | mAP: 91.07% -> 91.33% | Helped |
Closest papers by meaning
- GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition (CVPR 2018 · similarity 0.90)
- Learning Barycentric Representations of 3D Shapes for Sketch-Based 3D Shape Retrieval (CVPR 2017 · similarity 0.88)
- View-GCN: View-Based Graph Convolutional Network for 3D Shape Analysis (CVPR 2020 · similarity 0.88)
- Emphasizing 3D Properties in Recurrent Multi-View Aggregation for 3D Shape Retrieval (AAAI 2018 · similarity 0.87)
- Deep Sketch-Shape Hashing With Segmented 3D Stochastic Viewing (CVPR 2019 · similarity 0.87)
- Group-Pair Convolutional Neural Networks for Multi-View Based 3D Object Retrieval (AAAI 2018 · 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.