# Matching with AffNet based rectifications

arXiv: https://arxiv.org/abs/2207.14660 · HTML: https://mlsanity.com/paper/2207.14660/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 29 Jul 2022.

## Builds on (most cited first, 13 of 13)

- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction](https://mlsanity.com/paper/2109.00512/) (2021)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [Kornia: an Open Source Differentiable Computer Vision Library for PyTorch](https://mlsanity.com/paper/1910.02190/) (2019)
- [Image Matching across Wide Baselines: From Paper to Practice](https://mlsanity.com/paper/2003.01587/) (2020)
- [Working hard to know your neighbor's margins: Local descriptor learning loss](https://mlsanity.com/paper/1705.10872/) (2017)
- [D2D: Keypoint Extraction with Describe to Detect Approach](https://mlsanity.com/paper/2005.13605/) (2020)
- [MODS: Fast and Robust Method for Two-View Matching](https://mlsanity.com/paper/1503.02619/) (2015)
- [Single-Image Depth Prediction Makes Feature Matching Easier](https://mlsanity.com/paper/2008.09497/) (2020)
- [Radially-Distorted Conjugate Translations](https://mlsanity.com/paper/1711.11339/) (2017)
- [Minimal Solvers for Rectifying from Radially-Distorted Conjugate Translations](https://mlsanity.com/paper/1911.01507/) (2019)
- [Rectification from Radially-Distorted Scales](https://mlsanity.com/paper/1807.06110/) (2018)
- [Minimal Solvers for Rectifying from Radially-Distorted Scales and Change of Scales](https://mlsanity.com/paper/1907.11539/) (2019)

## Abstract (arXiv)

We consider the problem of two-view matching under significant viewpoint changes with view synthesis. We propose two novel methods, minimizing the view synthesis overhead. The first one, named DenseAffNet, uses dense affine shapes estimates from AffNet, which allows it to partition the image, rectifying each partition with just a single affine map. The second one, named DepthAffNet, combines information from depth maps and affine shapes estimates to produce different sets of rectifying affine maps for different image partitions. DenseAffNet is faster than the state-of-the-art and more accurate on generic scenes. DepthAffNet is on par with the state of the art on scenes containing large planes. The evaluation is performed on 3 public datasets - EVD Dataset, Strong ViewPoint Changes Dataset and IMC Phototourism Dataset.