Gravity Alignment for Single Panorama Depth Inference

Bergmann, Matheus A.; Pinto, Pedro; Silveira, Thiago L. T. da; Jung, Cláudio Rosito

doi:10.1109/sibgrapi54419.2021.00015

Cited by 3 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Como se pode perceber, a imagem apresenta fortes distorções visuais, sendo inclusive difícil a identificação dos elementos da cena (cadeiras, quadro, teto, etc.). Aplicando o algoritmo de correção de orientação proposto em [Bergmann et al 2021] gera a imagem mostrada na Figura 2.5b, que visualmente alinha o plano horizontal do mundo (sala de aula) com o equador da imagem esférica.…”

Section: Correção De Orientaçãounclassified

See 1 more Smart Citation

Processamento de Imagens Omnidirecionais e Aplicações

Silveira,

Jung

2023

Escola De Computação PPGC/UFRGS 50 Anos: Transformando Desafios Em Oportunidades Para O Futuro

View full text Add to dashboard Cite

Omnidirectional images and videos have been widely disseminated due to the popularization of devices for capture and visualization. Unlike images captured with perspective projection, omnidirectional media are defined on the surface of a sphere, having a field of view of 360 • × 180 • . Thus, they store the light intensities in the entire region around the capture point, with high potential for use in applications involving immersive augmented, mixed and virtual reality experiences. Although defined in the spherical domain, omnidirectional images are often mapped to a (multi)planar representation, which results in distorted images and degrades the performance of most traditional visual computing algorithms designed to work in the plane. This chapter reviews the spherical camera model, the most common capture devices, and popular (multi)planar representations of omnidirectional media. It also lists the main challenges of omnidirectional visual computing, focusing on the deep learning paradigm, and discusses potential applications. ResumoImagens e vídeos omnidirecionais têm sido amplamente difundidos devido à popularização de dispositivos para captura e visualização. Ao contrário das imagens capturadas com projeção em perspectiva, as mídias omnidirecionais são definidas sobre a superfície de uma esfera, tendo um campo de visão de 360 • × 180 • . Assim, elas armazenam as intensidades de luz em toda região em torno do ponto de captura, com alto potencial de uso em aplicações que envolvem experiências imersivas de realidade aumentada, mista e virtual. Embora definidas no domínio esférico, as imagens omnidirecionais muitas vezes são mapeadas para uma representação (multi) planar, o que resulta em imagens distorcidas Vídeo com a apresentação do capítulo: https://youtu.be/rqLWrSRm-Y0

show abstract

Section: Correção De Orientaçãounclassified

“…Figura 2.5: A (a) tilted 360 • capture (in ERP format) of the same scene as in Figura 2.1b and (b) its upright aligned version using the estimates from the method in[Bergmann et al 2021]. …”

mentioning

confidence: 99%

Processamento de Imagens Omnidirecionais e Aplicações

Silveira,

Jung

2023

Escola De Computação PPGC/UFRGS 50 Anos: Transformando Desafios Em Oportunidades Para O Futuro

View full text Add to dashboard Cite

show abstract

“…Then, they propose a projection function to map image edges onto the ground loor (assuming known camera height) and use a Hough transform-like voting scheme to obtain the room shape. This approach is more generic for not assuming Manhattan worlds but implicitly assumes that the panorama is gravity-aligned, which might not hold in practical situations [19].…”

Section: Layout Estimationmentioning

confidence: 99%

“…Moreover, spherical captures presenting rotations generate CMP images that are not aligned ś the faces in one capture might relate to a region comprising two or three faces in other captures ś which might highlight distortions. As such, it is advisable to perform image derotation [19] on the sphere before generating the CMP images, or to explore camera setups with small rotations as in [88ś91], which assume upright image captures. Finally, per-face depth estimation tends to produce discontinuities along face edges [37,159,168], and post-processing is required to obtain the full 3D model of the scene.…”

Section: Multi-view Stereo (Mvs)mentioning

confidence: 99%

3D Scene Geometry Estimation from 360° Imagery: A Survey

Silveira¹,

Pinto²,

Murrugarra-Llerena³

et al. 2022

ACM Comput. Surv.

Self Cite

View full text Add to dashboard Cite

This paper provides a comprehensive survey on pioneer and state-of-the-art 3D scene geometry estimation methodologies based on single, two, or multiple images captured under omnidirectional optics. We first revisit the basic concepts of the spherical camera model and review the most common acquisition technologies and representation formats suitable for omnidirectional (also called 360°, spherical or panoramic) images and videos. We then survey monocular layout and depth inference approaches, highlighting the recent advances in learning-based solutions suited for spherical data. The classical stereo matching is then revised on the spherical domain, where methodologies for detecting and describing sparse and dense features become crucial. The stereo matching concepts are then extrapolated for multiple view camera setups, categorizing them among light fields, multi-view stereo, and structure from motion (or visual simultaneous localization and mapping). We also compile and discuss commonly adopted datasets and figures of merit indicated for each purpose and list recent results for completeness. We conclude this paper by pointing out current and future trends.

show abstract

Visual Computing in 360°: Foundations, Challenges, and Applications

Silveira

Jung

2022

2022 35th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)

View full text Add to dashboard Cite

Gravity Alignment for Single Panorama Depth Inference

Cited by 3 publications

References 33 publications

Processamento de Imagens Omnidirecionais e Aplicações

Processamento de Imagens Omnidirecionais e Aplicações

3D Scene Geometry Estimation from 360° Imagery: A Survey

Visual Computing in 360°: Foundations, Challenges, and Applications

Contact Info

Product

Resources

About