Multi-View Image Fusion

Trinidad, Marc Comino; Martin-Brualla, Ricardo; Kainz, Florian; Kontkanen, Janne

doi:10.1109/iccv.2019.00420

Cited by 26 publications

(12 citation statements)

References 26 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Trinidad et al (2019) suggested three cases for image fusion which are colour conversion for the colour inferences on the monochrome display, HDR fusion to merge malaligned brake exposure and data transfer from a cost-beneficial camera in order to reproject a high-definition image [6].…”

Section: Methods Of Image Fusionmentioning

confidence: 99%

A Systematic Exploration of Image Fusion: A Review

Tushar

Nayak

2021

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Image fusion in the world of image analysis is a very trendy area of study. It has a broad variety of uses, such as monitoring, diagnosis and imaging, in different fields. All the methodologies have been addressed in this survey paper and different methods are presented to address the vulnerabilities of various issues. In this article, thorough review is carried out. Several attempts have been made to recognize the obstacles and indeed the milestones gained thus far. This paper subject to numerous study papers and have sought to cover any part of image fusion. On the basis of their domain, i.e., in the spatial and frequency domain, multi-scale transform image fusion methods were addressed. Next, with its main implementations and methods interconnected, image fusion is described in depth. Second, in tabulation, analysis of different fusion approaches is performed. Finally, the latest informative discussions of image fusion and potential aspects have been ended. This survey would be seen as a guideline for a domain connected to image fusion. The goal of the survey was to collectively examine the fundamental image fusion process with its categorization based on its modal systems and algorithms. The study shows that tremendous work has been done in the field of image fusion, but in this sense, there is still enormous space for fresh and creative work. The study also shows that any algorithm has its own strengths and disadvantages in this sense.

show abstract

Section: Methods Of Image Fusionmentioning

confidence: 99%

A Systematic Exploration of Image Fusion: A Review

Tushar

Nayak

2021

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

show abstract

“…To overcome the problem of relative movements between pixels, dense correspondence searching and alignment subnets are integrated into the CNN models, e.g. (Kalantari and Ramomoorthi 2017) (Chen et al 2020) (Trinidad et al 2019), to improve the reconstruction quality. Since the alignment results may not be perfect all the time, some recent works, e.g.…”

Section: Related Workmentioning

confidence: 99%

MIEHDR CNN: Main Image Enhancement based Ghost-Free High Dynamic Range Imaging using Dual-Lens Systems

Xuan

et al. 2021

AAAI

View full text Add to dashboard Cite

We study the High Dynamic Range (HDR) imaging problem using two Low Dynamic Range (LDR) images that are shot from dual-lens systems in a single shot time with different exposures. In most of the related HDR imaging methods, the problem is usually solved by Multiple Images Merging, i.e. the final HDR image is fused from pixels of all the input LDR images. However, ghost artifacts can be hardly avoided using this strategy. Instead of directly merging the multiple LDR inputs, we use an indirect way which enhances the main image, i.e. the short exposure image IS, using the long exposure image IL serving as guidance. In detail, we propose a new model, named MIEHDR CNN model, which consists of three subnets, i.e. Soft Warp CNN, 3D Guided Denoising CNN and Fusion CNN. The Soft Warp CNN aligns IL to get the aligned result ILA using the soft exposed result of IS as reference. The 3D Guided Denoising CNN denoises the soft exposed result of IS using ILA as guidance, whose result are fed into the Fusion CNN with IS to get the HDR result. The MIEHDR CNN model is implemented by MindSpore and experimental results show that we can outperform related methods largely and avoid ghost artifacts.

show abstract

“…3). Multi-view image fusion [62] was proposed to fuse misaligned photos from different camera sensors. It can transfer details from a highquality DSLR image to images taken by a VR180 camera [63].…”

Section: General Scenesmentioning

confidence: 99%

VR content creation and exploration with deep learning: A survey

Wang

Lyu

et al. 2020

Comp. Visual Media

View full text Add to dashboard Cite

Virtual reality (VR) offers an artificial, computer generated simulation of a real life environment. It originated in the 1960s and has evolved to provide increasing immersion, interactivity, imagination, and intelligence. Because deep learning systems are able to represent and compose information at various levels in a deep hierarchical fashion, they can build very powerful models which leverage large quantities of visual media data. Intelligence of VR methods and applications has been significantly boosted by the recent developments in deep learning techniques. VR content creation and exploration relates to image and video analysis, synthesis and editing, so deep learning methods such as fully convolutional networks and general adversarial networks are widely employed, designed specifically to handle panoramic images and video and virtual 3D scenes. This article surveys recent research that uses such deep learning methods for VR content creation and exploration. It considers the problems involved, and discusses possible future directions in this active and emerging research area. Keywords virtual reality; deep learning; neural networks; 360 • image and video virtual content

show abstract

Multi-View Image Fusion

Cited by 26 publications

References 26 publications

A Systematic Exploration of Image Fusion: A Review

A Systematic Exploration of Image Fusion: A Review

MIEHDR CNN: Main Image Enhancement based Ghost-Free High Dynamic Range Imaging using Dual-Lens Systems

VR content creation and exploration with deep learning: A survey

Contact Info

Product

Resources

About