# Deep Fundamental Matrix Estimation without Correspondences

arXiv: https://arxiv.org/abs/1810.01575 · HTML: https://mlsanity.com/paper/1810.01575/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Oct 2018.

## Built on by (most cited first, 15 of 15)

- [Wide-Baseline Relative Camera Pose Estimation with Directional Learning](https://mlsanity.com/paper/2106.03336/) (2021)
- [Planar Surface Reconstruction from Sparse Views](https://mlsanity.com/paper/2103.14644/) (2021)
- [The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs](https://mlsanity.com/paper/2208.08988/) (2022)
- [Deep Learning for Camera Calibration and Beyond: A Survey](https://mlsanity.com/paper/2303.10559/) (2023)
- [Two-View Geometry Scoring Without Correspondences](https://mlsanity.com/paper/2306.01596/) (2023)
- [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025)
- [Robust Long-Range Perception Against Sensor Misalignment in Autonomous Vehicles](https://mlsanity.com/paper/2408.11196/) (2024)
- [RelMobNet: End-to-end relative camera pose estimation using a robust two-stage training](https://mlsanity.com/paper/2202.12838/) (2022)
- [RLSAC: Reinforcement Learning enhanced Sample Consensus for End-to-End Robust Estimation](https://mlsanity.com/paper/2308.05318/) (2023)
- [A Revisit of the Normalized Eight-Point Algorithm and A Self-Supervised Deep Solution](https://mlsanity.com/paper/2304.10771/) (2023)
- [Multi-task Learning for Camera Calibration](https://mlsanity.com/paper/2211.12432/) (2022)
- [A Comparative Study of Vision Transformers and CNNs for Few-Shot Rigid Transformation and Fundamental Matrix Estimation](https://mlsanity.com/paper/2510.04794/) (2025)
- [GeoBlur: Epipolar Geometry Estimation from a Single Motion-Blurred Image](https://mlsanity.com/paper/2605.01552/) (2026)
- [Efficient 3D Content Reconstruction and Generation](https://mlsanity.com/paper/2605.18052/) (2026)
- [DiffSAC: Diffusion-guided Sampling for Consensus-based Robust Estimation](https://mlsanity.com/paper/2608.30603/) (2026)

## Abstract (arXiv)

Estimating fundamental matrices is a classic problem in computer vision. Traditional methods rely heavily on the correctness of estimated key-point correspondences, which can be noisy and unreliable. As a result, it is difficult for these methods to handle image pairs with large occlusion or significantly different camera poses. In this paper, we propose novel neural network architectures to estimate fundamental matrices in an end-to-end manner without relying on point correspondences. New modules and layers are introduced in order to preserve mathematical properties of the fundamental matrix as a homogeneous rank-2 matrix with seven degrees of freedom. We analyze performance of the proposed models using various metrics on the KITTI dataset, and show that they achieve competitive performance with traditional methods without the need for extracting correspondences.