Research map / 3D vision / Human pose estimation
Progressive Correspondence Pruning by Consensus Learning
Chen Zhao, Yixiao Ge, Feng Zhu, Rui Zhao, Hongsheng Li, Mathieu Salzmann
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 |
|---|---|---|---|
| use annular convolution instead of MLP and max-pooling for local aggregation (ablation) | CLNet · YFCC100M | AUC@5: 31.99 -> 32.79 | Improved |
| add local consensus learning (ablation) | CLNet · YFCC100M | AUC@5: 29.99 -> 30.94 | Improved |
| add global consensus learning on top of local consensus (ablation) | CLNet · YFCC100M | AUC@5: 30.94 -> 31.70 | Improved |
| add local-to-global consensus learning (ablation) | CLNet · YFCC100M | AUC@5: 29.99 -> 31.70 | Improved |
| add adaptive temperature in the classification loss (ablation) | CLNet · YFCC100M | AUC@5: 31.70 -> 32.79 | Improved |
| use consensus-guided pruning instead of iterating PointCN twice to sample candidates (ablation) | CLNet · YFCC100M | AUC@5 | Improved |
| add a second pruning iteration (ablation) | CLNet · YFCC100M | inlier ratio: 20% to 80% | Improved |
| add pruning iterations beyond the second (ablation) | CLNet · YFCC100M | AUC@5 | Hurt |
| use a 25% sampling ratio of candidates (ablation) | CLNet · YFCC100M | AUC@5 | Improved |
| add CLNet re-ranking of SFRS retrieval | SFRS · Tokyo 24/7 | Recall@1: 85.4 -> 91.4 | Improved |
| use CLNet instead of RANSAC for re-ranking SFRS | SFRS · Tokyo 24/7 | Recall@1: 88.6 -> 91.4 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- SuperGlue — SuperGlue: Learning Feature Matching With Graph Neural Networks (CVPR 2020) · better on 3 of 3 shared results
- OANet — OANet: Learning Two-View Correspondences and Geometry Using Order-Aware Network (TPAMI 2020) · better on 1 of 1 shared result
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
- Progressive Neighbor Consistency Mining for Correspondence Pruning (CVPR 2023 · similarity 0.90)
- Scalable and Generalizable Correspondence Pruning via Geometry-Consistent Pre-Training (TPAMI 2026 · similarity 0.90)
- BCLNet: Bilateral Consensus Learning for Two-View Correspondence Pruning (AAAI 2024 · similarity 0.89)
- Graph Context Transformation Learning for Progressive Correspondence Pruning (AAAI 2024 · similarity 0.88)
- VSFormer: Visual-Spatial Fusion Transformer for Correspondence Pruning (AAAI 2024 · similarity 0.86)
- Progressive Correspondence Regenerator for Robust 3D Registration (CVPR 2025 · similarity 0.86)
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.
