A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Deep Homography Estimation for Dynamic Scenes
[article]
2020
arXiv
pre-print
Preserved Fulltext
Our experiments show that our method can robustly estimate homography for challenging scenarios with dynamic scenes, blur artifacts, or lack of textures. ...
To estimate a homography of a dynamic scene in a more principled way, we need to identify the dynamic content. ...
We thank Luke Ding for helping develop our dataset. ...
arXiv:2004.02132v1
fatcat:b3ftjjdvznavjlbivwa4bojp3q
Deep Homography Estimation in Dynamic Surgical Scenes for Laparoscopic Camera Motion Extraction
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The synthetic camera motion serves as a supervisory signal for camera motion estimation that is invariant to object and tool motion. ...
to videos of laparoscopic interventions, outperforming classical homography estimation approaches in both, precision by 41%, and runtime on a CPU by 43%. ...
Conclusion In this work we supervisedly learn homography estimation in dynamic surgical scenes. ...
arXiv:2109.15098v2
fatcat:uq5t4qtcdzagjd5nperfhn2imy
Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this paper, we introduce a new framework for unsupervised deep homography estimation. Our contributions are 3 folds. ...
First, unlike previous methods that regress 4 offsets for a homography, we propose a homography flow representation, which can be estimated by a weighted sum of 8 pre-defined homography flow bases. ...
Except for the RE, the other 4 scenes are challenging for the homography estimation. ...
arXiv:2103.15346v2
fatcat:db46koewpvfyphchj2nmrtmyn4
DeepMeshFlow: Content Adaptive Mesh Deformation for Robust Image Registration
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Deep homography methods, on the other hand, are free from such problem by learning deep features for robust performance. However, a homography is limited to plane motions. ...
Moreover, a comprehensive dataset is presented, covering various scenes for training and testing. ...
as low-textured scenes, parallax and dynamic objects, but also due to its widespread applications, such [8] , Meshflow [9] and our proposed Deep Meshflow. ...
arXiv:1912.05131v1
fatcat:m7r7qolmavbitpq2yom7xpjyxu
Content-Aware Unsupervised Deep Homography Estimation
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Homography estimation is a basic image alignment method in many applications. ...
In the spirit of the RANSAC procedure in traditional methods, we specifically learn an outlier mask to only select reliable regions for homography estimation. ...
Consequently, feature-based homography estimation is usually a challenging task for these non-regular scenes. ...
arXiv:1909.05983v2
fatcat:2bdekbj3pzbuxeem3dzvejvhmy
Deep Exposure Fusion with Deghosting via Homography Estimation and Attention Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Our network integrates together homography estimation for compensating camera motion, attention mechanism for correcting remaining misalignment and moving pixels, and adversarial learning for alleviating ...
This paper proposes a deep network for exposure fusion. For reducing the potential ghosting problem, our network only takes two images, an underexposed image and an overexposed one. ...
Our contribution are as follows. • We propose the first deep network for estimating a homography between two differently exposed images and integrate it into an exposure fusion network. ...
arXiv:2004.09089v1
fatcat:xnqir7ppb5csvia73poz3nxuby
Road-aware Monocular Structure from Motion and Homography Estimation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Recently, much progress has been made in using deep neural networks for SFM and homography estimation respectively. ...
However, directly applying existing methods for ground plane homography estimation may fail because the road is often a small part of the scene. ...
Recently deep learning based methods are popular for visual odometry estimation. ...
arXiv:2112.08635v1
fatcat:tsu4gardqfgqtn75bmvkzp6cmy
Depth-Aware Multi-Grid Deep Homography Estimation with Contextual Correlation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Traditional homography estimation methods heavily depend on the quantity and distribution of feature correspondences, leading to poor robustness in low-texture scenes. ...
The codes and models will be available at https://github.com/nie-lang/Multi-Grid-Deep-Homography. ...
[16] apply deep learning to homography estimation for the first time, developing a VGG-style homography regression network. ...
arXiv:2107.02524v2
fatcat:etpm43j4obgxhlr23u4l7gfyeu
Unsupervised Homography Estimation with Coplanarity-Aware GAN
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Estimating homography from an image pair is a fundamental problem in image alignment. ...
In this work, we propose a novel method HomoGAN to guide unsupervised homography estimation to focus on the dominant plane. ...
LF), where the last four are challenging scenes for homography estimation. ...
arXiv:2205.03821v1
fatcat:rvk6d6sgxnhvnpl6a77jsxgebq
Geometry-Aware Deep Network for Single-Image Novel View Synthesis
2018
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Specifically, we approximate a real-world scene by a fixed number of planes, and learn to predict a set of homographies and their corresponding region masks to transform the input image into a novel view ...
In particular, we target real-world scenes with rich geometric structure, a challenging task due to the large appearance variations of such scenes and the lack of simple 3D models to represent them. ...
The Titan X used for this research was donated by the NVIDIA Corporation. ...
doi:10.1109/cvpr.2018.00485
dblp:conf/cvpr/LiuHS18
fatcat:x4ss6im5zbfjnjkx2csx3oxite
Learning Edge-Preserved Image Stitching from Large-Baseline Deep Homography
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Experimental results demonstrate that our homography module significantly outperforms the existing deep homography methods in the large baseline scenes. ...
First, we propose a large-baseline deep homography module to estimate the accurate projective transformation between the reference image and the target image in different scales of features. ...
Unlike the existing deep methods that estimate the homography in small-baseline scenes, the proposed approach is specially designed for large-baseline homography estimation, laying a solid foundation for ...
arXiv:2012.06194v1
fatcat:g6tuaihpkjhwrcbsb7uq6lxrk4
Geometry-aware Deep Network for Single-Image Novel View Synthesis
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Specifically, we approximate a real-world scene by a fixed number of planes, and learn to predict a set of homographies and their corresponding region masks to transform the input image into a novel view ...
In particular, we target real-world scenes with rich geometric structure, a challenging task due to the large appearance variations of such scenes and the lack of simple 3D models to represent them. ...
Acknowledgments This work was done when the first author was working in Data61, CSIRO, Australia.The Titan X used for this research was donated by the NVIDIA Corporation. ...
arXiv:1804.06008v1
fatcat:wrz7dz75hffwvpbhlpqow2m474
Homography estimation along short videos by recurrent convolutional regression network
2020
Mathematical Foundations of Computing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, we propose a new deep-learning based method for homography estimation along videos by exploiting temporal dynamics across frames. ...
estimating the parameters of homography. ...
HomographyNet is a deep-learning based method for homography estimation and we use the architecture and default setting as described in [12] . ...
doi:10.3934/mfc.2020014
fatcat:yzfunsczjnbkdgh5kazcrbdp6u
EVDodgeNet: Deep Dynamic Obstacle Dodging with Event Cameras
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this paper, we present a deep learning -- based solution for dodging multiple dynamic obstacles on a quadrotor with a single event camera and on-board computation. ...
Our approach uses a series of shallow neural networks for estimating both the ego-motion and the motion of independently moving objects. ...
To enable robust homography estimation, we laid down carpets of different textures on the ground to obtain strong contours in event frames (Refer to Fig. S6) . We ...
arXiv:1906.02919v3
fatcat:whkdu6dndjghdjfjttvmur3ouy
Deep Features Homography Transformation Fusion Network—A Universal Foreground Segmentation Algorithm for PTZ Cameras and a Comparative Study
2020
Sensors
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In the kernel of HTFnetSeg, there is the combination of an unsupervised semantic attention homography estimation network (SAHnet) for frames alignment and a spatial transformed deep features fusion network ...
In this paper, an end-to-end deep features homography transformation and fusion network based foreground segmentation method (HTFnetSeg) is proposed for surveillance videos recorded by PTZ cameras. ...
Acknowledgments: The authors would like to thank the benchmark website for CDnet2014 (www. changedetection.net) and LASIESTA (www.gti.ssr.upm.es/data/LASIESTA). ...
doi:10.3390/s20123420
pmid:32560491
pmcid:PMC7348900
fatcat:yyflwxzttzazfckyykelceb4vu
« Previous
Showing results 1 — 15 out of 1,078 results