The repository contains our dataset and C++ implementation of the CVPR 2022 paper, Geometric Structure Preserving Warp for Natural Image Stitching.

Geometric Structure Preserving Warp for Natural Image Stitching

This repository contains our dataset and C++ implementation of the CVPR 2022 paper, Geometric Structure Preserving Warp for Natural Image Stitching. If you use any code or data from our work, please cite our paper.


Figure 1. An example of stitching 10 images. (a) The AutoStitch's [8] result is severely distorted. (b) The person on the right side is distorted in the APAP's [7] result. (c) Several misalignments (red and green closeup) in the ELA’s [9] result. (d) The SPW's [10] result exhibits significant wrong scale at the right end. (e) There are distortions in the red box, e.g., the floor and carpet are curved in the result obtained by GSP [2]. (f) Our result preserves the salient geometric structures in scene.

Download

  1. Paper(available soon)
  2. Supplementary(available soon)
  3. Code
  4. DataSet (GES-50)

Code

1. Usage

(1). Download code and comile.
	You need Opencv 4.4.0, VLFEAT, Eigen.
(2). Download dataset to "input-data" folder.
(3). Run project.

Or

(4). We provide scripts that make it easier to test data. The following are the steps:
(5). Edit "RUN_EXE.bat". 
	Change "file=\RUN_FILE.txt" and "\GES_Stitching.exe" to corresponding path.
(6). List dataset names you want to test in "RUN_FILE.txt".
(7). Click "RUN_EXE.bat".

Notice:

  • If you make changes to the code, you can copy .exe from the "x64" to the root directory and rename it to "GES_Stitching.exe" after running project.
  • If the .exe output errors, try to run the project to get a new .exe.

You can find results in folder "input-data".

Dataset

1. Introduction

There are 50 diversified and challenging dataset (26 from [1–7] and 24 collected by ourselves). The numbers of images range from 2 to 35.

2. Usage

(1). Copy dataset to folder "input-data" in project.
(2). Make sure the file "xxx-STITCH-GRAPH.txt" in each dataset correspond to the name of this dataset.
(3). You can change the relation between the images by modifying the file "xxx-STITCH-GRAPH.txt".

Contact

Feel free to contact me if there is any question ([email protected]).

Reference

  1. Che-Han Chang, Yoichi Sato, and Yung-Yu Chuang. Shapepreserving half-projective warps for image stitching. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3254–3261, 2014.
  2. Yu-Sheng Chen and Yung-Yu Chuang. Natural image stitching with the global similarity prior. In European conference on computer vision, pages 186–201. Springer, 2016.
  3. Junhong Gao, Seon Joo Kim, and Michael S Brown. Constructing image panoramas using dual-homography warping. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 49–56. IEEE, 2011.
  4. Qi Jia, ZhengJun Li, Xin Fan, Haotian Zhao, Shiyu Teng,Xinchen Ye, and Longin Jan Latecki. Leveraging line-point consistence to preserve structures for wide parallax image stitching. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 12186–12195,2021.
  5. Chung-Ching Lin, Sharathchandra U Pankanti, Karthikeyan Natesan Ramamurthy, and Aleksandr Y Aravkin. Adaptive as-natural-as-possible image stitching. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1155–1163, 2015.
  6. Yoshikuni Nomura, Li Zhang, and Shree K Nayar. Scene collages and flexible camera arrays. In Proceedings of the 18th Eurographics conference on Rendering Techniques, pages 127–138, 2007.
  7. Julio Zaragoza, Tat-Jun Chin, Michael S Brown, and David Suter. As-projective-as-possible image stitching with moving dlt. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2339–2346, 2013.
  8. Matthew Brown and David G Lowe. Automatic panoramic image stitching using invariant features. International journal of computer vision, 74(1):59–73, 2007.
  9. Jing Li, Zhengming Wang, Shiming Lai, Yongping Zhai, and Maojun Zhang. Parallax-tolerant image stitching based on robust elastic warping. IEEE Transactions on multimedia, 20(7):1672–1687, 2017.
  10. Tianli Liao and Nan Li. Single-perspective warps in natural image stitching. IEEE Transactions on Image Processing, 29:724–735, 2019.
Similar Resources

[CVPR 2021] NormalFusion: Real-Time Acquisition of Surface Normals for High-Resolution RGB-D Scanning

NormalFusion: Real-Time Acquisition of Surface Normals for High-Resolution RGB-D Scanning Project Page | Paper | Supplemental material #1 | Supplement

Apr 25, 2022

HybridPose: 6D Object Pose Estimation under Hybrid Representation (CVPR 2020)

HybridPose: 6D Object Pose Estimation under Hybrid Representation (CVPR 2020)

HybridPose: 6D Object Pose Estimation under Hybrid Representations This repository contains authors' implementation of HybridPose: 6D Object Pose Esti

May 13, 2022

Training and fine-tuning YOLOv4 Tiny on custom object detection dataset for Taiwanese traffic

Training and fine-tuning YOLOv4 Tiny on custom object detection dataset for Taiwanese traffic

Object Detection on Taiwanese Traffic using YOLOv4 Tiny Exploration of YOLOv4 Tiny on custom Taiwanese traffic dataset Trained and tested AlexeyAB's D

Mar 7, 2022

FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling

FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling

FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling Comparisons of Running Time of Our Method with SOTA methods RandLA and KPConv:

May 10, 2022

Super Mario Remake using C++, SFML, and Image Processing which was a project for Structure Programming Course, 1st Year

Super Mario Remake using C++, SFML, and Image Processing which was a project for Structure Programming Course, 1st Year

Super Mario Remake We use : C++ in OOP concepts SFML for game animations and sound effects. Image processing (Tensorflow and openCV) to add additional

Nov 20, 2021

UAV images dataset for moving object detection

UAV images dataset for moving object detection

PESMOD PESMOD (PExels Small Moving Object Detection) dataset consists of high resolution aerial images in which moving objects are labelled manually.

May 9, 2022

Video Recoloring via Spatial-Temporal Geometric Palettes

Video Recoloring via Spatial-Temporal Geometric Palettes

Video Recoloring via Spatial-Temporal Geometric Palettes This is the source code of the paper: Video Recoloring via Spatial-Temporal Geometric Palette

Feb 16, 2022

Prepares the Audi Autonomous Driving Dataset (A2D2) for ROS

Prepares the Audi Autonomous Driving Dataset (A2D2) for ROS

A2D2 ROS Preparer Purpose A2D2 ROS Preparer converts the Audi Autonomous Driving Dataset (A2D2) to a rosbag enabling the usage of ROS tools on this da

Jan 29, 2022

Repository for course content (homeworks, projects, recitation exercises) of CSCI 1300 in Spring 2022.

CSCI1300 Spring 2022 Repository for course content (e.g. homework assignments, project write-ups, recitation exercises) of CSCI 1300 in Spring 2022. C

Apr 6, 2022
Code and Data for our CVPR 2021 paper "Structured Scene Memory for Vision-Language Navigation"

SSM-VLN Code and Data for our CVPR 2021 paper "Structured Scene Memory for Vision-Language Navigation". Environment Installation Download Room-to-Room

May 8, 2022
Dataset Synthesizer - NVIDIA Deep learning Dataset Synthesizer (NDDS)
Dataset Synthesizer - NVIDIA Deep learning Dataset Synthesizer (NDDS)

NVIDIA Deep learning Dataset Synthesizer (NDDS) Overview NDDS is a UE4 plugin from NVIDIA to empower computer vision researchers to export high-qualit

May 13, 2022
DeepI2P - Image-to-Point Cloud Registration via Deep Classification. CVPR 2021
DeepI2P - Image-to-Point Cloud Registration via Deep Classification. CVPR 2021

#DeepI2P: Image-to-Point Cloud Registration via Deep Classification Summary Video PyTorch implementation for our CVPR 2021 paper DeepI2P. DeepI2P solv

May 4, 2022
ncnn demo of DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction
ncnn demo of DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction

DocTr-ncnn ncnn demo of DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction model support: 1.Document Segmentation 2

May 10, 2022
This is the code of our paper An Efficient Training Approach for Very Large Scale Face Recognition or F²C for simplicity.
This is the code of our paper An Efficient Training Approach for Very Large Scale Face Recognition or F²C for simplicity.

Fast Face Classification (F²C) This is the code of our paper An Efficient Training Approach for Very Large Scale Face Recognition or F²C for simplicit

Jun 27, 2021
NLP-based perching trajectory generation presented in our paper "Perception-Aware Perching on Powerlines with Multirotors".
NLP-based perching trajectory generation presented in our paper

Perception-Aware Perching on Powerlines with Multirotors This repo contains the code for the NLP-based perching trajectory generation presented in our

Apr 13, 2022
Frog is an integration of memory-based natural language processing (NLP) modules developed for Dutch. All NLP modules are based on Timbl, the Tilburg memory-based learning software package.

Frog - A Tagger-Lemmatizer-Morphological-Analyzer-Dependency-Parser for Dutch Copyright 2006-2020 Ko van der Sloot, Maarten van Gompel, Antal van den

Mar 5, 2022
Python and C++ implementation of "MarkerPose: Robust real-time planar target tracking for accurate stereo pose estimation". Accepted at LXCV Workshop @ CVPR 2021.
Python and C++ implementation of

MarkerPose: Robust Real-time Planar Target Tracking for Accurate Stereo Pose Estimation This is a PyTorch and LibTorch implementation of MarkerPose: a

Apr 28, 2022
Official PyTorch Code of GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection (CVPR 2021)
Official PyTorch Code of GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection (CVPR 2021)

GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Mo

May 18, 2022