# Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes arXiv: https://arxiv.org/abs/2109.03585 ยท HTML: https://mlsanity.com/paper/2109.03585/ ## Key facts - Cited by 7 papers in the map (data through 14 Oct 2026). - Builds on 30 of its 68 references that are in the map. - First posted on arXiv 8 Sep 2021. ## Builds on (most cited first, 30 of 30) - [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019) - [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017) - [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015) - [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018) - [Learning Enriched Features for Real Image Restoration and Enhancement](https://mlsanity.com/paper/2003.06792/) (2020) - [LIFT: Learned Invariant Feature Transform](https://mlsanity.com/paper/1603.09114/) (2016) - [HPatches: A benchmark and evaluation of handcrafted and learned local descriptors](https://mlsanity.com/paper/1704.05939/) (2017) - [Large-Scale Image Retrieval with Attentive Deep Local Features](https://mlsanity.com/paper/1612.06321/) (2016) - [Residual Non-local Attention Networks for Image Restoration](https://mlsanity.com/paper/1903.10082/) (2019) - [Image Matching across Wide Baselines: From Paper to Practice](https://mlsanity.com/paper/2003.01587/) (2020) - [R2D2: Repeatable and Reliable Detector and Descriptor](https://mlsanity.com/paper/1906.06195/) (2019) - [Learning to Find Good Correspondences](https://mlsanity.com/paper/1711.05971/) (2017) - [CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction](https://mlsanity.com/paper/1704.03489/) (2017) - [LF-Net: Learning Local Features from Images](https://mlsanity.com/paper/1805.09662/) (2018) - [A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising](https://mlsanity.com/paper/2003.12751/) (2020) - [SOSNet: Second Order Similarity Regularization for Local Descriptor Learning](https://mlsanity.com/paper/1904.05019/) (2019) - [Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses](https://mlsanity.com/paper/1905.04132/) (2019) - [Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters](https://mlsanity.com/paper/1904.00889/) (2019) - [Learning to Compare Image Patches via Convolutional Neural Networks](https://mlsanity.com/paper/1504.03641/) (2015) - [Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration](https://mlsanity.com/paper/1903.08817/) (2019) - [DeepSFM: Structure From Motion Via Deep Bundle Adjustment](https://mlsanity.com/paper/1912.09697/) (2019) - [TILDE: A Temporally Invariant Learned DEtector](https://mlsanity.com/paper/1411.4568/) (2014) - [GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs](https://mlsanity.com/paper/1911.05932/) (2019) - [Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task](https://mlsanity.com/paper/1912.00623/) (2019) - [Quad-networks: unsupervised learning to rank for interest point detection](https://mlsanity.com/paper/1611.07571/) (2016) - [RF-Net: An End-to-End Image Matching Network based on Receptive Field](https://mlsanity.com/paper/1906.00604/) (2019) - [An Evaluation of Feature Matchers for Fundamental Matrix Estimation](https://mlsanity.com/paper/1908.09474/) (2019) - [PN-Net: Conjoined Triple Deep Network for Learning Local Image Descriptors](https://mlsanity.com/paper/1601.05030/) (2016) - [No Fear of the Dark: Image Retrieval under Varying Illumination Conditions](https://mlsanity.com/paper/1908.08999/) (2019) - [Leveraging Outdoor Webcams for Local Descriptor Learning](https://mlsanity.com/paper/1901.09780/) (2019) ## Built on by (most cited first, 7 of 7) - [Human Pose Estimation in Extremely Low-Light Conditions](https://mlsanity.com/paper/2303.15410/) (2023) - [UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Training](https://mlsanity.com/paper/2302.06891/) (2023) - [Self-Aligned Concave Curve: Illumination Enhancement for Unsupervised Adaptation](https://mlsanity.com/paper/2210.03792/) (2022) - [Robust Scene Inference under Noise-Blur Dual Corruptions](https://mlsanity.com/paper/2207.11643/) (2022) - [SuperGF: Unifying Local and Global Features for Visual Localization](https://mlsanity.com/paper/2212.13105/) (2022) - [LIME-Eval: Rethinking Low-light Image Enhancement Evaluation via Object Detection](https://mlsanity.com/paper/2410.08810/) (2024) - [A Multi-Scale Spatial Attention-Based Zero-Shot Learning Framework for Low-Light Image Enhancement](https://mlsanity.com/paper/2506.18323/) (2025) ## Abstract (arXiv) This paper considers matching images of low-light scenes, aiming to widen the frontier of SfM and visual SLAM applications. Recent image sensors can record the brightness of scenes with more than eight-bit precision, available in their RAW-format image. We are interested in making full use of such high-precision information to match extremely low-light scene images that conventional methods cannot handle. For extreme low-light scenes, even if some of their brightness information exists in the RAW format images' low bits, the standard raw image processing on cameras fails to utilize them properly. As was recently shown by Chen et al., CNNs can learn to produce images with a natural appearance from such RAW-format images. To consider if and how well we can utilize such information stored in RAW-format images for image matching, we have created a new dataset named MID (matching in the dark). Using it, we experimentally evaluated combinations of eight image-enhancing methods and eleven image matching methods consisting of classical/neural local descriptors and classical/neural initial point-matching methods. The results show the advantage of using the RAW-format images and the strengths and weaknesses of the above component methods. They also imply there is room for further research.