Enabling Multiview- and Light Field-Video for Veridical Visual Experiences

Herfet, Thorsten; Lange, Tobias

doi:10.1109/compcomm.2018.8780991

“…While this puts the principal point in the centre of the views by simulating the images being taken by a single camera, it comes at the price of a small loss of resolution due to cropping. In addition we use one image from the Stanford gantry dataset (l eg o kni g ht s) [Stanford, 2021], and four high resolution images from the Technicolor (bi r t hd a y, pai nt er ) [Sabater et al, 2017] and SAUCE datasets (cel l i st , f i r e_d ancer ) [Herfet et al, 2018, Trottnow et al, 2019. These high resolution images, with a wider baseline, pose some difficulty for traditional light field methods which are not designed for such sets.…”

Section: Comparing Novel View Synthesismentioning

confidence: 99%

Geometrically reconstructing confocal microscopy images for modelling the retinal microvasculature as a 3D cylindrical network

Troendle¹,

Barabás²,

Curtis³

2022

24th Irish Machine Vision and Image Processing Conference

0

View full text Add to dashboard Cite

Microvascular networks can be modelled as a network of connected cylinders. Presently, however, there are limited approaches with which to recover these networks from biomedical images. We have therefore developed and implemented computer algorithms to geometrically reconstruct three-dimensional (3D) retinal microvascular networks from micrometre-scale imagery, resulting in a concise representation of two endpoints and radius for each cylinder detected within a delimited text file. This format is suitable for a variety of purposes, including efficient simulations of molecular delivery. Here, we detail a semi-automated pipeline consisting of the detection of retinal microvascular volumes within 3D imaging datasets, the enhancement and analysis of these volumes for reconstruction, and the geometric construction algorithm itself, which converts voxel data into representative 3D cylindrical objects.

show abstract

“…While this puts the principal point in the centre of the views by simulating the images being taken by a single camera, it comes at the price of a small loss of resolution due to cropping. In addition we use one image from the Stanford gantry dataset (l eg o kni g ht s) [Stanford, 2021], and four high resolution images from the Technicolor (bi r t hd a y, pai nt er ) [Sabater et al, 2017] and SAUCE datasets (cel l i st , f i r e_d ancer ) [Herfet et al, 2018, Trottnow et al, 2019. These high resolution images, with a wider baseline, pose some difficulty for traditional light field methods which are not designed for such sets.…”

Section: Comparing Novel View Synthesismentioning

confidence: 99%

Triple Loss based Satellite Image Localisation for Aerial Platforms

Herrera¹,

McCarhy²,

McDonald³

2022

24th Irish Machine Vision and Image Processing Conference

0

View full text Add to dashboard Cite

We present a vision-based technique for aerial platform localisation using satellite imagery. Our approach applies a modified VGG16 network in conjunction with a triplet loss to encode aerial views as discriminative scene embeddings. The platform is localised by comparing the encodding of its current view with a database of pre-encoded embeddings using a cosine similarity metric. Recent image-based localisation research has shown potential for such learned embeddings, however, to ensure reliable matching they require dense sampling of views of the environment, thereby limiting their operational area. In contrast, the combination of our proposed architecture in conjunction with the triplet loss shows robustness over greater spatial shifts, reducing the need for dense sampling. We demonstrate these improvements through comparison with a state-of-the-art approach using simulated ground truth sequences derived from a real-world satellite dataset covering a 1.5km × 1km region in Karslruhe.

show abstract

“…While this puts the principal point in the centre of the views by simulating the images being taken by a single camera, it comes at the price of a small loss of resolution due to cropping. In addition we use one image from the Stanford gantry dataset (l eg o kni g ht s) [Stanford, 2021], and four high resolution images from the Technicolor (bi r t hd a y, pai nt er ) [Sabater et al, 2017] and SAUCE datasets (cel l i st , f i r e_d ancer ) [Herfet et al, 2018, Trottnow et al, 2019. These high resolution images, with a wider baseline, pose some difficulty for traditional light field methods which are not designed for such sets.…”

Section: Comparing Novel View Synthesismentioning

confidence: 99%

Acoustic Source Localization Using Straight Line Approximations

Bagchi¹,

Fréin²

2022

24th Irish Machine Vision and Image Processing Conference

0

View full text Add to dashboard Cite

The short paper extends an acoustic signal delay estimation method to general anechoic scenario using image processing techniques. The technique proposed in this paper localizes acoustic speech sources by creating a matrix of phase versus frequency histograms, where the same phases are stacked in appropriate bins. With larger delays and multiple sources coexisting in the same matrix, it becomes cluttered with activated bins. This results in high intensity spots on the spectrogram, making source discrimination difficult. In this paper, we have employed morphological filtering, chain-coding and straight line approximations to ignore noise and enhance the target signal features. Lastly, Hough transform is used for the source localization. The resulting estimates are accurate and invariant to the sampling-rate and shall have application in acoustic source separation.

show abstract

Enabling Multiview- and Light Field-Video for Veridical Visual Experiences

Cited by 18 publications

References 8 publications

Geometrically reconstructing confocal microscopy images for modelling the retinal microvasculature as a 3D cylindrical network

Geometrically reconstructing confocal microscopy images for modelling the retinal microvasculature as a 3D cylindrical network

Triple Loss based Satellite Image Localisation for Aerial Platforms

Acoustic Source Localization Using Straight Line Approximations

Contact Info

Product

Resources

About