Animating Still Landscape Photographs Through Cloud Motion Creation

Jhou, Wei-Cih; Cheng, Winton

doi:10.1109/tmm.2015.2500031

Cited by 19 publications

(12 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jhou and Cheng [47] animate clouds present in a given image through automatic motion creation. Two parameters, cloudiness and cloud structure, are extracted as cues from the image and a content-aware wind field incorporating mean flow, and turbulence is generated to synthesize the cloud flow.…”

Section: Procedural Animationmentioning

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

Section: Procedural Animationmentioning

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

show abstract

“…Creating animation from a single image has been a longstanding research problem in computer vision and computer graphics. Early work on this topic relies on either user interactions [5] or domain-specific knowledge [36,13]. Most related to our approach, a datadriven hallucination method [27] was proposed to synthesize a time-lapse video from a single outdoor image by a color transfer algorithm based on a reference video.…”

Section: Related Workmentioning

confidence: 99%

End-To-End Time-Lapse Video Synthesis From a Single Outdoor Image

Nam

Chai

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Time-lapse videos usually contain visually appealing content but are often difficult and costly to create. In this paper, we present an end-to-end solution to synthesize a time-lapse video from a single outdoor image using deep neural networks. Our key idea is to train a conditional generative adversarial network based on existing datasets of time-lapse videos and image sequences. We propose a multiframe joint conditional generation framework to effectively learn the correlation between the illumination change of an outdoor scene and the time of the day. We further present a multi-domain training scheme for robust training of our generative models from two datasets with different distributions and missing timestamp labels. Compared to alternative time-lapse video synthesis algorithms, our method uses the timestamp as the control variable and does not require a reference video to guide the synthesis of the final output. We conduct ablation studies to validate our algorithm and compare with state-of-the-art techniques both qualitatively and quantitatively.

show abstract

“…However, there are studies that require only one still image to reconstruct the motion of an object in the photograph. A study [16] has carried out to create the cloud motion, which is much harder than animating the rigid objects. On the other hand, in order to reconstruct a 3D scene, localizing the object is critical even if the system uses the RGB-D camera.…”

Section: Related Workmentioning

confidence: 99%

A fast 3D scene reconstructing method using continuous video

Sung

Lin

2017

J Image Video Proc.

View full text Add to dashboard Cite

Accurate 3D measuring systems thrive in the past few years. Most of them are based on laser scanners because these laser scanners are able to acquire 3D information directly and precisely in real time. However, comparing to the conventional cameras, these kinds of equipment are usually expensive and they are not commonly available to customers. Moreover, laser scanners interfere easily with each other sensors of the same type. On the other hand, computer vision-based 3D measuring techniques use stereo matching to acquire the cameras' relative position and then estimate the 3D location of points on the image. Because this kind of systems needs additional estimation of the 3D information, systems with real time capability often relies on heavy parallelism that prevents implementation on mobile devices. Inspired by the structure from motion systems, we propose a system that reconstructs sparse feature points to a 3D point cloud using a mono video sequence so as to achieve higher computation efficiency. The system keeps tracking all detected feature points and calculates both the amount of these feature points and their moving distances. We only use the key frames to estimate the current position of the camera in order to reduce the computation load and the noise interference on the system. Furthermore, for the sake of avoiding duplicate 3D points, the system reconstructs the 2D point only when the point shifts out of the boundary of a camera. In our experiments, we show that our system is able to be implemented on tablets and can achieve state-of-the-art accuracy with a denser point cloud with high speed.

show abstract

Animating Still Landscape Photographs Through Cloud Motion Creation

Cited by 19 publications

References 37 publications

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

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

End-To-End Time-Lapse Video Synthesis From a Single Outdoor Image

A fast 3D scene reconstructing method using continuous video

Contact Info

Product

Resources

About