Research map / Image generation / Image restoration
Arbicon-Net: Arbitrary Continuous Geometric Transformation Networks for Image Registration
Jianchun Chen, Lingjing Wang, Xiang Li, Yi Fang
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 |
|---|---|---|---|
| predict dense displacement field with MLP instead of fixed-parameter geometric model | 4D-conv correlation network · PF-Pascal weak supervision | PCK: 76.5 -> 77.3 | Improved |
| replace TPS model with Arbicon-Net displacement predictor | CNNGeo · Proposal Flow strong supervision | PCK: 78.5 -> 84.3 | Improved |
| replace TPS model with Arbicon-Net displacement predictor | CNNGeo-4D · Synthetic diffeomorphic transformation | MSE: 0.0037 -> 0.0002 | Improved |
| replace TPS model with Arbicon-Net displacement predictor | CNNGeo · Proposal Flow strong supervision | Esmooth: 0.013 -> 0.008 | Improved |
| replace TPS with Arbicon-Net when synthetic TPS control points grow 4x4 to 6x6 | CNNGeo-4D · Synthetic TPS transformations | MSE: about 1.5 times lower MSE | Improved |
Closest papers by meaning
- Convolutional Neural Network Architecture for Geometric Matching (CVPR 2017 · similarity 0.86)
- Recurrent Registration Neural Networks for Deformable Image Registration (NeurIPS 2019 · similarity 0.86)
- Discrete-Continuous Transformation Matching for Dense Semantic Correspondence (TPAMI 2018 · similarity 0.86)
- GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences (CVPR 2020 · similarity 0.85)
- Pyramidal Semantic Correspondence Networks (TPAMI 2021 · similarity 0.85)
- CARL: A Framework for Equivariant Image Registration (CVPR 2025 · similarity 0.85)
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.
