Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes

09/08/2021
by   Wenzheng Song, et al.
11

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.

READ FULL TEXT

page 3

page 5

page 8

page 11

page 12

page 13

page 15

page 16

research
09/05/2023

RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Image

High dynamic range (HDR) images capture much more intensity levels than ...
research
06/03/2022

Learning sRGB-to-Raw-RGB De-rendering with Content-Aware Metadata

Most camera images are rendered and saved in the standard RGB (sRGB) for...
research
02/28/2020

Automatically matching topographical measurements of cartridge cases using a record linkage framework

Firing a gun leaves marks on cartridge cases which purportedly uniquely ...
research
12/08/2020

Raw Image Deblurring

Deep learning-based blind image deblurring plays an essential role in so...
research
01/04/2018

A Large Dataset for Improving Patch Matching

We propose a new dataset for learning local image descriptors which can ...
research
07/26/2017

Modelling the Scene Dependent Imaging in Cameras with a Deep Neural Network

We present a novel deep learning framework that models the scene depende...
research
07/06/2022

Local Relighting of Real Scenes

We introduce the task of local relighting, which changes a photograph of...

Please sign up or login with your details

Forgot password? Click here to reset