Research map / 3D vision / Face and shape
MVTN: Multi-View Transformation Network for 3D Shape Recognition
Abdullah Hamdi, Silvio Giancola, Bernard Ghanem
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 |
|---|---|---|---|
| add MVTN view-point regression (ablation) | MVCNN, 12 views · ModelNet40 | overall accuracy: 90.4 -> 92.6 | Improved |
| add MVTN view-point regression (ablation) | RotationNet, 12 views · ModelNet40 | overall accuracy: 91.6 -> 93.2 | Improved |
| add MVTN view-point regression (ablation) | ViewGCN, 12 views · ModelNet40 | overall accuracy: 93.0 -> 93.8 | Improved |
| add MVTN view-point regression (ablation) | ViewGCN, 20 views · ModelNet40 | overall accuracy: 93.3 -> 93.5 | Improved |
| add MVTN view-point regression (ablation) | ViewGCN* · ScanObjectNN PB_T50_RS | overall accuracy: 80.5 -> 82.8 | Improved |
| regress view-points with MVTN instead of late fusion of point and multi-view networks (ablation) | MVCNN with PointNet · ModelNet40 | overall accuracy: 88.4 -> 91.8 | Improved |
| use ResNet-34 backbone instead of ResNet-18 (ablation) | MVTN-spherical PointNet · ModelNet40 | overall accuracy: 93.41 -> 92.83 | No clear effect |
| use DGCNN point encoder instead of PointNet (ablation) | MVTN-spherical ResNet-18 · ModelNet40 | overall accuracy: 93.41 -> 93.26 | No clear effect |
| use spherical instead of circular initial views (ablation) | MVTN ResNet-18 PointNet · ModelNet40 | overall accuracy: 92.83 -> 93.41 | Improved |
| transfer MVTN views learned with MVCNN to ViewGCN (ablation) | ViewGCN · ModelNet40 | overall accuracy: 92.4 -> 93.1 | Improved |
| randomize object color in training instead of white (ablation) | MVTN · ModelNet40 | overall accuracy: 93.3 -> 93.4 | No clear effect |
| predict view-points directly (MVTN-direct) with more than four views (ablation) | MVTN-direct · ModelNet40 | overall accuracy | Hurt |
Later papers that compared with this method
1 later accepted paper reports MVTN as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- LBONet: Supervised Spectral Descriptors for Shape Analysis (TPAMI 2025 · better on 0 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ViewGCN* — View-GCN: View-Based Graph Convolutional Network for 3D Shape Analysis (CVPR 2020) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- MVTN: Learning Multi-view Transformations for 3D Understanding (IJCV 2024 · similarity 0.98)
- Learning View-Based Graph Convolutional Network for Multi-View 3D Shape Analysis (TPAMI 2022 · similarity 0.91)
- View-GCN: View-Based Graph Convolutional Network for 3D Shape Analysis (CVPR 2020 · similarity 0.90)
- MLVCNN: Multi-Loop-View Convolutional Neural Network for 3D Shape Retrieval (AAAI 2019 · similarity 0.89)
- MVImgNet: A Large-Scale Dataset of Multi-View Images (CVPR 2023 · similarity 0.88)
- RotationNet for Joint Object Categorization and Unsupervised Pose Estimation from Multi-View Images (TPAMI 2019 · 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.
