Direct space-time trajectory control for visual media editing

Santosa, Stephanie; Chevalier, Fanny; Balakrishnan, Ravin; Singh, Karan

doi:10.1145/2470654.2466148

Cited by 14 publications

(9 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Different interfaces and interaction paradigms have been explored in the fields of computer graphics and human-computer interaction, for instance for lighting [Kerr and Pellacini 2009;Ou et al 2012], material editing [Kerr and Pellacini 2010;Colbert et al 2006], video editing [Santosa et al 2013;Goldman et al 2008] or painting [Haeberli 1990]. In this paper, we perform the first study focusing on the particular topic of light field editing.…”

Section: Related Workmentioning

confidence: 99%

How do people edit light fields?

et al. 2014

View full text Add to dashboard Cite

We present a thorough study to evaluate different light field editing interfaces, tools and workflows from a user perspective. This is of special relevance given the multidimensional nature of light fields, which may make common image editing tasks become complex in light field space. We additionally investigate the potential benefits of using depth information when editing, and the limitations imposed by imperfect depth reconstruction using current techniques. We perform two different experiments, collecting both objective and subjective data from a varied number of editing tasks of increasing complexity based on local point-and-click tools. In the first experiment, we rely on perfect depth from synthetic light fields, and focus on simple edits. This allows us to gain basic insight on light field editing, and to design a more advanced editing interface. This is then used in the second experiment, employing real light fields with imperfect reconstructed depth, and covering more advanced editing tasks. Our study shows that users can edit light fields with our tested interface and tools, even in the presence of imperfect depth. They follow different workflows depending on the task at hand, mostly relying on a combination of different depth cues. Last, we confirm our findings by asking a set of artists to freely edit both real and synthetic light fields.

show abstract

Section: Related Workmentioning

confidence: 99%

How do people edit light fields?

et al. 2014

View full text Add to dashboard Cite

show abstract

“…Furthermore, editing is limited to selecting and merging existing superpixels. Boundaries can also be propagated using optical flow estimates [Tsai et al 2012;Santosa et al 2013], or tracked keypoints [Lebeda et al 2016] (combined with color models in [Li et al 2005]). Trimap propagation using optical flow has featured in video matting [Chuang et al 2002], and provide a good overview of methods to that point.…”

Section: Related Workmentioning

confidence: 99%

Roto++

Viola

Starck

et al. 2016

ACM Trans. Graph.

View full text Add to dashboard Cite

Figure 1: An example of our new Roto++ tool working with a professional artist to increase productivity. The artist has already specified a number of keyframes but is not satisfied with one of the intermediate frames. Under standard baselines, correcting the erroneous curve requires moving the individual control points of the spline. Using our new shape model we are able to provide an Intelligent Drag Tool that can generate likely shapes given the other keyframes. In our new interaction, the user simply selects the incorrect points and drags them all towards the correct shape. Our shape model then correctly proposes the new control point locations, allowing the correction to be performed in a single operation.

show abstract

“…Cette diversification explique probablement la variété des techniques d'interaction présentées dans ce papier. Par exemple, plusieurs techniques d'interaction ontété proposées dans le contexte de la navigation 3D [8,24], la modélisation 3D [57,49,43], la création d'animations [54,44], la génération de terrains [8,16], la création de routes [36], le design automobile [4,17,18,2]. Nous constatons, cependant, que peu de travaux portent sur le domaine du son 3D.…”

Section: Manipulation De La Caméraunclassified

“…La figure 3 montre le positionnement de notreétude, laquelle se situeà la croisée de plusieurs domaines tels que la visualisation de l'information, la navigation 3D, la création d'animations, la vision par ordinateur et la modélisation. A titre d'exemples relatifsà ces domaines, on peut citer l'utilisation de tracés de courbes pour filtrer une visualisation 3D [53,56], créer des animations [14,44,54], définir des trajectoires de caméra dans une scène 3D [34] ou encore créer des routes dans des systèmes de génie civil [36].…”

Section: Introductionunclassified

A design space for three-dimensional curve edition

Jacob

Bailly

Lecolinet

et al. 2014

Proceedings of the 26th Conference on l'Interaction Homme-Machine

View full text Add to dashboard Cite

La création et l'édition de courbes 3D intervient dans de nombreux domaines d'application comme la CAO, l'édition de contenus spatio-temporels dans une vidéo ou encore la génération de terrains et de routes. Cette diversité a conduità une dispersion des travaux au sein de plusieurs communautés telles que SIGCHI ou SIGGRAPH. Cet article propose un espace de caractérisation visantà rassembler les techniques proposées pour la création et l'édition de courbes 3D. Cet espace est décomposé en deux axes: dispositif et langage afin de décrire et comparer les techniques existantes.

show abstract

Direct space-time trajectory control for visual media editing

Cited by 14 publications

References 20 publications

How do people edit light fields?

How do people edit light fields?

Roto++

A design space for three-dimensional curve edition

Contact Info

Product

Resources

About