Heliometric Stereo: Shape from Sun Position

Abrams, Austin; Hawley, Christopher; Pless, Robert

doi:10.1007/978-3-642-33709-3_26

Cited by 55 publications

(78 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ackermann et al [3] and Abrams et al [1] use time-lapse sequences captured by static outdoor webcams. Since both approaches model the illumination as a distant point light (the sun) with a constant ambient light, they require many months of images to avoid coplanar light directions in photometric stereo.…”

Section: Related Workmentioning

confidence: 99%

“…They undergo image selection to remove images of bad weather and night time and process hundreds of selected images. Abrams et al [1] propose an iterative, non-linear optimization of ambient light, shadows, light color, surface normals, radiometric calibration, and exposures. It is a huge optimization using 500 images of careful selection.…”

Section: Related Workmentioning

confidence: 99%

“…The shadow detection method for [2] which also estimates albedo, surface normals, and ambient light is compared using the same one day images. Abrams et al [1]'s results using 500 images of many months are obtained from their original paper. For comparison, we used the same color map defined in their paper.…”

Section: Qualitative Evaluationmentioning

confidence: 99%

“…As mentioned in [1], this reference normal is from Google Earth, and many locations in the reference have substantial angular error because it does not consider trees and bushes in the scene. Therefore, for evaluation, we compute the robustness statistics used in the Middlebury stereo dataset [31].…”

Section: Quantitative Evaluationmentioning

confidence: 99%

“…Table 1 shows the stability of our method. We tested the previous methods [1], [2] and ours on 15 single-day datasets. Each set(day) is selected from an individual month among 15 months of data.…”

Section: Quantitative Evaluationmentioning

confidence: 99%

See 4 more Smart Citations

One-day outdoor photometric stereo via skylight estimation

Jung

Lee

Kweon

2015

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

We present an outdoor photometric stereo method using images captured in a single day. We simulate a sky hemisphere for each image according to its GPS and timestamp, and parameterize the obtained sky hemisphere into a quadratic skylight and a Gaussian sunlight distribution. Unlike previous works which usually model outdoor illumination as a sum of constant ambient light and a distant point light, our method models natural illumination according to a popular sky model and thus provides sufficient constraints for shape reconstruction from one day images. We generate pixel profiles of uniformly sampled unit vectors for the corresponding time of captures and evaluate them using correlation with the actual pixel profiles. The estimated surface normal is refined by MRF optimization. We have tested our method to recover objects and scenes of various sizes in real-world outdoor daylight.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Qualitative Evaluationmentioning

confidence: 99%

Section: Quantitative Evaluationmentioning

confidence: 99%

Section: Quantitative Evaluationmentioning

confidence: 99%

See 3 more Smart Citations

One-day outdoor photometric stereo via skylight estimation

Jung

Lee

Kweon

2015

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

Dealing with Missing Depth: Recent Advances in Depth Image Completion and Estimation

Atapour-Abarghouei

Breckon

2019

RGB-D Image Analysis and Processing

View full text Add to dashboard Cite

Even though obtaining 3D information has received significant attention in scene capture systems in recent years, there are currently numerous challenges within scene depth estimation which is one of the fundamental parts of any 3D vision system focusing on RGB-D images. This has lead to the creation of an area of research where the goal is to complete the missing 3D information post capture. In many downstream applications, incomplete scene depth is of limited value and thus techniques are required to fill the holes that exist in terms of both missing depth and colour scene information. An analogous problem exists within the scope of scene filling post object removal in the same context. Although considerable research has resulted in notable progress in the synthetic expansion or reconstruction of missing colour scene information in both statistical and structural forms, work on the plausible completion of missing scene depth is contrastingly limited. Furthermore, recent advances in machine learning using deep neural networks have enabled complete depth estimation in a monocular or stereo framework circumnavigating the need for any completion post-processing hence increasing both efficiency and functionality. In this chapter, a brief overview of the advances in the state-of-the-art approaches within RGB-D completion is presented whilst noting related solutions in the space of traditional texture synthesis and colour image completion for hole filling. Recent advances in employing learning-based techniques for this and related depth estimation tasks are also explored and presented.

show abstract

Domain Adaptation via Image Style Transfer

Atapour-Abarghouei

Breckon

2020

Domain Adaptation in Computer Vision With Deep Learning

View full text Add to dashboard Cite

While recent growth in modern machine learning techniques has led to remarkable strides in computer vision applications, one of the most significant challenges facing learning-based vision systems is the scarcity of large, high-fidelity datasets required for training large-scale models. This has necessitated the creation of transfer learning and domain adaptation as a highly-active area of research, wherein the objective is to adapt a model trained on one set of data from a specific domain to perform well on previously-unseen data from a different domain. In this chapter, we use monocular depth estimation as a means of demonstrating a new perspective on domain adaptation. Most monocular depth estimation approaches either rely on large quantities of ground truth depth data, which is extremely expensive and difficult to obtain, or alternatively predict disparity as an intermediary step using a secondary supervisory signal leading to blurring and other artefacts. Training a depth estimation model using pixel-perfect synthetic depth images can resolve most of these issues but introduces the problem of domain shift from synthetic to real-world data. Here, we take advantage of recent advances in image style transfer and its connection with domain adaptation to predict depth from a single colour image based on training over a large corpus of synthetic data obtained from a virtual environment. Experimental results point to the impressive capabilities of style transfer used as a means of adapting the model to unseen data from a different domain.

show abstract

Heliometric Stereo: Shape from Sun Position

Cited by 55 publications

References 22 publications

One-day outdoor photometric stereo via skylight estimation

One-day outdoor photometric stereo via skylight estimation

Dealing with Missing Depth: Recent Advances in Depth Image Completion and Estimation

Domain Adaptation via Image Style Transfer

Contact Info

Product

Resources

About