Incorporating Cloud Distribution in Sky Representation

Peng, Kuan-Chuan; Chen, Tsuhan

doi:10.1109/iccv.2013.267

Cited by 4 publications

(4 citation statements)

References 20 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Images have been used to estimate cloud cover for a variety of purposes, including image retrieval [15], graphics [16], weather estimation [8] and solar power forecasting [2,17]. This paper extends our previous work [18], which was, to our knowledge, the first work to attempt to use ground shadows to estimate a cloud layer.…”

Section: Related Workmentioning

confidence: 70%

“…They use a Gaussian mixture model to represent a set of simple color features combined with a Markov Random field for enforcing spatial coherence. Peng et al [16] address the same problem, but incorporate a physically based sky appearance model [28]. Veikherman et al [14] propose a tomographic approach to building a 3D model of clouds from imagery captured by a network of sky cameras.…”

Section: Estimating Outdoor Illuminationmentioning

confidence: 99%

See 1 more Smart Citation

Cloudmaps from static ground-view video

Jacobs

Workman

Souvenir

2016

Image and Vision Computing

View full text Add to dashboard Cite

Cloud shadows dramatically affect the appearance of outdoor scenes. We describe three approaches that use video of cloud shadows to estimate a cloudmap, a spatio-temporal function that represents the clouds passing over the scene. Two of the methods make assumptions about the camera and/or scene geometry. The third method uses techniques from manifold learning and does not require such assumptions. None of the methods require directly viewing the clouds, but instead use the pattern of intensity changes caused by the cloud shadows. An accurate estimate of the cloudmap has potential applications in solar power estimation and forecasting, surveillance, and graphics. We present a quantitative evaluation of our methods on synthetic scenes and show qualitative results on real scenes. We also demonstrate the use of a cloudmap for foreground object detection and video editing.

show abstract

Section: Related Workmentioning

confidence: 70%

Section: Estimating Outdoor Illuminationmentioning

confidence: 99%

Cloudmaps from static ground-view video

Jacobs

Workman

Souvenir

2016

Image and Vision Computing

View full text Add to dashboard Cite

show abstract

“…Image-based Cloud images captured from terrestrial angles have been utilized to model the cloud shapes. Peng and Chen [73] propose to capture variable cloudiness in input images by formulating it as a labeling problem. Each sky pixel is assigned a label based on the Igawa sky model (uses solar zenith, azimuth, etc.)…”

Section: Geometric Ebert Inmentioning

confidence: 99%

A survey of modeling, rendering and animation of clouds in computer graphics

Goswami¹

2020

Vis Comput

View full text Add to dashboard Cite

Clouds play an important role in enhancing the realism of outdoor scenes in computer graphics (CG). Realistic cloud generation is a challenging task, which entails processes such as modeling, photorealistic rendering and simulation of the clouds. To these ends, several techniques have been proposed within the CG community in the last 4 decades with one or more of the above stated focuses. The growth of modern hardware has also enabled development of techniques that can achieve cloud display and animation at interactive frame rates. In this survey, we review the prominent work in the domain and also summarize the evolution of the research over the time.

show abstract

“…It is difficult to segment an image to model cloud distributions in the sky since clouds are ill-posed structures that do not have concrete forms and visually appear with varying levels of transparency around the boundaries [12]- [14]. With only a single photo as source, we cannot exploit structure matching between two images for cloud recognition [15].…”

Section: Introductionmentioning

confidence: 99%

Animating Still Landscape Photographs Through Cloud Motion Creation

Jhou

Cheng

2016

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Animating landscape photographs can create an engaging viewing experience and has long been an active area of multimedia research. Images can be used to create an illusion of movement, thereby providing more vivid and interesting visuals. Among numerous objects in visual scenes, clouds appear as a common element in landscape photos but are challenging to manipulate because clouds are ill-posed structures without concrete forms and present motion with very high degrees of freedom and arbitrary shape deformation. This paper addresses the generation of dynamic imagery from a still photo through automatic motion creation. First, a cloud appearance model is acquired by representing each pixel in the sky region as a combination of two computable image properties, i.e., Cloudiness estimates cloud density and Cloud Structure gives the corresponding cloud shape and texture. Then, based on the obtained Cloudiness and Cloud Structure, a content-aware wind field is generated to synthesize the motion of cloud flow. Experimental results demonstrate that our approach can work well on various types of cloud images and produce visually convincing dynamic imagery of landscape photos. Furthermore, we showcased several extended multimedia applications to validate that the proposed framework is generic and widely extensible to other vapor-like objects like mist and smoke. Please see http://mclab.citi.sinica.edu.tw/demo/dynamicimagery.htm for demos.

show abstract

Incorporating Cloud Distribution in Sky Representation

Abstract: Abstract

Cited by 4 publications

References 20 publications

Cloudmaps from static ground-view video

Cloudmaps from static ground-view video

A survey of modeling, rendering and animation of clouds in computer graphics

Animating Still Landscape Photographs Through Cloud Motion Creation

Contact Info

Product

Resources

About