# Structure-from-Motion using Dense CNN Features with Keypoint Relocalization

arXiv: https://arxiv.org/abs/1805.03879 · HTML: https://mlsanity.com/paper/1805.03879/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2018.

## Built on by (most cited first, 9 of 9)

- [ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer](https://mlsanity.com/paper/2208.14201/) (2022)
- [OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models](https://mlsanity.com/paper/2301.07673/) (2023)
- [Detector-Free Structure from Motion](https://mlsanity.com/paper/2306.15669/) (2023)
- [Object-Guided Day-Night Visual Localization in Urban Scenes](https://mlsanity.com/paper/2202.04445/) (2022)
- [Identifying and Extracting Football Features from Real-World Media Sources using Only Synthetic Training Data](https://mlsanity.com/paper/2209.13254/) (2022)
- [LGFCTR: Local and Global Feature Convolutional Transformer for Image Matching](https://mlsanity.com/paper/2311.17571/) (2023)
- [GOEmbed: Gradient Origin Embeddings for Representation Agnostic 3D Feature Learning](https://mlsanity.com/paper/2312.08744/) (2023)
- [NeRF-Supervised Feature Point Detection and Description](https://mlsanity.com/paper/2403.08156/) (2024)
- [SGFormer: Structure-Guided Transformer for Robust Local Feature Matching](https://mlsanity.com/paper/2608.03423/) (2026)

## Abstract (arXiv)

Structure from Motion (SfM) using imagery that involves extreme appearance changes is yet a challenging task due to a loss of feature repeatability. Using feature correspondences obtained by matching densely extracted convolutional neural network (CNN) features significantly improves the SfM reconstruction capability. However, the reconstruction accuracy is limited by the spatial resolution of the extracted CNN features which is not even pixel-level accuracy in the existing approach. Providing dense feature matches with precise keypoint positions is not trivial because of memory limitation and computational burden of dense features. To achieve accurate SfM reconstruction with highly repeatable dense features, we propose an SfM pipeline that uses dense CNN features with relocalization of keypoint position that can efficiently and accurately provide pixel-level feature correspondences. Then, we demonstrate on the Aachen Day-Night dataset that the proposed SfM using dense CNN features with the keypoint relocalization outperforms a state-of-the-art SfM (COLMAP using RootSIFT) by a large margin.