Research map / 3D vision / 3D generation
Group-Pair Convolutional Neural Networks for Multi-View Based 3D Object 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 |
|---|---|---|---|
| Replace hand-crafted-feature retrieval algorithms with end-to-end GPCNN | GPCNN · MVRED | NN: +3.5%-42% | Helped |
| Use GPCNN instead of CSPC on small ETH dataset | GPCNN · ETH | PR curve | Helped |
| Group-pair multi-view input with view pooling instead of Siamese pair input (ablation) | GPCNN · NTU-60 | NN: +37%-57% over Siamese/VGG | Helped |
| Siamese pair-wise learning instead of single-network VGG-16 + NN (ablation) | CNN retrieval baseline · ETH, NTU, MVRED | retrieval metrics | Helped |
| Element-wise mean view pooling instead of max (ablation) | GPCNN · 3D retrieval | retrieval performance | Hurt |
Closest papers by meaning
- GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition (CVPR 2018 · similarity 0.90)
- DeepCCFV: Camera Constraint-Free Multi-View Convolutional Neural Network for 3D Object Retrieval (AAAI 2019 · similarity 0.88)
- ImageNet3D: Towards General-Purpose Object-Level 3D Understanding (NeurIPS 2024 · similarity 0.85)
- Duoduo CLIP: Efficient 3D Understanding with Multi-View Images (ICLR 2025 · similarity 0.85)
- Dual Pose-invariant Embeddings: Learning Category and Object-specific Discriminative Representations for Recognition and Retrieval (CVPR 2024 · similarity 0.84)
- LION: Linear Group RNN for 3D Object Detection in Point Clouds (NeurIPS 2024 · similarity 0.84)
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.