Correcting perceived perspective distortions using object specific planar transformations

Tehrani, Mahdi Abbaspour; Majumder, Aditi; Gopi, M.

doi:10.1109/iccphot.2016.7492868

Cited by 16 publications

(9 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If we do, it may be that we recognise the scene as of a certain familiar kind. Or it may be that we rely on pictorial cues, which are comparatively distance invariant (albeit subject to perspective distortions / foreshortening: Tehrani et al, 2016), and which are unaffected by telestereoscopic viewing (which increases binocular disparity without reducing viewing distance).…”

Section: Telestereoscopic Viewingmentioning

confidence: 99%

Does Vergence Affect Perceived Size?

Linton

2020

Preprint

View full text Add to dashboard Cite

Vergence (the angular rotation of the eyes) is thought to provide essential distance information for size constancy (perceiving an object as having a constant physical size). Evidence for this comes from the fact that a target with a constant retinal size appears to shrink as the rotation of the eyes increases (indicating that the target has reduced in distance). This reduction in perceived size is supposed to maintain a constant perception of physical size in natural viewing conditions by cancelling out the increasing size of the retinal image as an object moves closer. Whilst this hypothesis has been extensively tested over the last 200 years, it has always been tested in the presence of confounding cues such as a changing retinal image or cognitive cues to distance.Testing members of the public with normal vision, we control for these confounding cues and find no evidence of vergence size constancy. Statement of RelevanceThis work has important implications for the neural basis of size constancy and for multisensory integration. First, leading work on the neural basis of size constancy cannot differentiate between recurrent processes in V1 (based on triangulation cues, such as vergence) and top-down processing (based on pictorial cues). Since our work challenges the existence of vergence size constancy, and therefore much of the basis of the recurrent processing account, our work indicates that top-down processing is likely to have a much more important role in size constancy than previously thought.Second, vergence size constancy is thought to be largely responsible for the apparent integration of the retinal image with proprioceptive distance information from the hand in the Taylor illusion (an afterimage of the hand viewed in darkness appears to shrink as the observer's hand is moved closer). This explanation for the Taylor illusion is challenged, and a cognitive account proposed instead.

show abstract

Section: Telestereoscopic Viewingmentioning

confidence: 99%

Does Vergence Affect Perceived Size?

Linton

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Since the tilted angle α is not known, a third point is required to add one more constraint on the centre location curve parametric equations. This equation is depicted in (25).…”

Section: Locating the Centre From Three Pointsmentioning

confidence: 99%

“…Figure 1 illustrates the three forms of distortions of a target in the image. Existing methods tried to model the perspective effect [24], some methods are based on the hypothesis constraints by the scene [25], like the position of the vanishing points within the image [26], or benefit from the stereo setup for adding up depth constraints to improve the model for measurements [27]. On the contrary, many other methods are based on learning patterns from a set of image data [13] like face recognition, ball tracking [28] and learning depth [29]- [31].…”

Section: Introductionmentioning

confidence: 99%

Perspective Distortion Modeling for Image Measurements

et al. 2020

View full text Add to dashboard Cite

A perspective distortion modelling for monocular view that is based on the fundamentals of perspective projection is presented in this work. Perspective projection is considered to be the most ideal and realistic model among others, which depicts image formation in monocular vision. There are many approaches trying to model and estimate the perspective effects in images. Some approaches try to learn and model the distortion parameters from a set of training data that work only for a predefined structure. None of the existing methods provide deep understanding of the nature of perspective problems. Perspective distortions, in fact, can be described by three different perspective effects. These effects are pose, distance and foreshortening. They are the cause of the aberrant appearance of object shapes in images. Understanding these phenomena have long been an interesting topic for artists, designers and scientists. In many cases, this problem has to be necessarily taken into consideration when dealing with image diagnostics, high and accurate image measurement, as well as accurate pose estimation from images. In this work, a perspective distortion model for every effect is developed while elaborating the nature of perspective effects. A distortion factor for every effect is derived, then followed by proposed methods, which allows extracting the true target pose and distance, and correcting image measurements.

show abstract

“…Recent work [8] optimizes the parameters in the Pannini projection [7] to preserve regions with greater low-level saliency and straight lines. Interactive methods [10,11,12,13] require a user to outline regions of interest that should be preserved or require input from a user to determine projection orientation [14]. Our approach is content-based and fully automatic.…”

Section: Related Workmentioning

confidence: 99%

“…conformality, or other low-level cues [7,8,9], optionally using manual input to know what is worth preserving [10,11,12,13,14]. However, all prior automatic content-based projection methods implicitly assume that the viewpoint of the input 360 • image is fixed.…”

Section: Introductionmentioning

confidence: 99%

Snap Angle Prediction for 360$$^{\circ }$$ Panoramas

Xiong

Grauman

2018

Computer Vision – ECCV 2018

View full text Add to dashboard Cite

360 • panoramas are a rich medium, yet notoriously difficult to visualize in the 2D image plane. We explore how intelligent rotations of a spherical image may enable content-aware projection with fewer perceptible distortions. Whereas existing approaches assume the viewpoint is fixed, intuitively some viewing angles within the sphere preserve high-level objects better than others. To discover the relationship between these optimal snap angles and the spherical panorama's content, we develop a reinforcement learning approach for the cubemap projection model. Implemented as a deep recurrent neural network, our method selects a sequence of rotation actions and receives reward for avoiding cube boundaries that overlap with important foreground objects. We show our approach creates more visually pleasing panoramas while using 5x less computation than the baseline.

show abstract

Correcting perceived perspective distortions using object specific planar transformations

Cited by 16 publications

References 27 publications

Does Vergence Affect Perceived Size?

Does Vergence Affect Perceived Size?

Perspective Distortion Modeling for Image Measurements

Snap Angle Prediction for 360$$^{\circ }$$ Panoramas

Contact Info

Product

Resources

About