[Bf-committers] GSOC 2013 Proposal

[Xavier Thomas]

A good starting  place for poisson based image manipulation in Blender
would be the Inpaint node.


2013/4/15 Ton Roosendaal <ton at blender.org>

> Hi Siddharth,
>
> All three proposals are very cool, but quite more suitable for GIMP than
> for Blender. For GIMP such filters can well live locally as a plugin. In
> Blender it means to think in the context of tools and usablity. Where would
> you add this, and how then have users interact?
>
> -Ton-
>
> ------------------------------------------------------------------------
> Ton Roosendaal  Blender Foundation   ton at blender.org    www.blender.org
> Blender Institute   Entrepotdok 57A  1018AD Amsterdam   The Netherlands
>
> On 12 Apr, 2013, at 5:25, Siddharth wrote:
>
> > Hi,
> >
> > I am currently pursuing MS by Research in the field of computer vision
> and
> > image processing at IIIT- Hyderabad, India. I am interested in working
> for
> > Blender organization this summer in a GSoC project.
> >
> >
> > Some of my own ideas:
> >
> > a) *Interactive Poisson Image Blending*
> >
> > Image editing tasks concern either global changes (color/intensity
> > corrections, filters, deformations) or local changes concerned to a
> > selection. Here we are interested in achieving local changes, ones that
> are
> > restricted to a region manually selected (ROI), in a seamless and
> > effortless manner. The extent of the changes ranges from slight
> distortions
> > to complete replacement by novel content. Examples:Inserting objects,
> Color
> > Transfer, Feature Exchange, Texture Flattening, Local illumination
> changes,
> > etc.
> >
> >
> http://cs.engr.uky.edu/~jacobs/classes/2010_photo/readings/PoissonImageEditing.pdf
> >
> > b) *Color2Gray*
> >
> > Visually important image features often disappear when color images are
> > converted to grayscale. This algorithm reduces such losses by attempting
> to
> > preserve the salient features of the color image. The Color2Gray results
> > offer viewers salient information missing from previous grayscale image
> > creation methods.
> >
> > http://www.cse.cuhk.edu.hk/~leojia/papers/decolorization_iccp12.pdf
> >
> > c) *Domain Transform for Edge-Aware Image Processing
> > (Non-Photorealistic Animation and Rendering)*
> >
> > The processing involves high-quality edge-preserving filtering of images
> > (better than bilateral filter). The filter is applied on several image
> > processing tasks including edge-preserving smoothing, Depth-of-field
> > effects, stylization, detail enhancement, edge enhancement and
> pencil/color
> > pencil sketch.
> >
> >
> http://www.inf.ufrgs.br/~eslgastal/DomainTransform/Gastal_Oliveira_SIGGRAPH2011_Domain_Transform.pdf
> >
> > What are your views about this?
> >
> > Best Regards,
> > Siddharth
> >
> > --
> > Live as if you were to die tomorrow. Learn as if you were to live
> forever -
> > M K Gandhi
> > _______________________________________________
> > Bf-committers mailing list
> > Bf-committers at blender.org
> > http://lists.blender.org/mailman/listinfo/bf-committers
>
> _______________________________________________
> Bf-committers mailing list
> Bf-committers at blender.org
> http://lists.blender.org/mailman/listinfo/bf-committers
>