What are "crawling artifacts" in computer graphics? - graphics

I am reading a paper where it says something about that. Googling didn't help that much.
The full sentence is in the section 3.1 of this paper:
http://gfx.cs.princeton.edu/pubs/Cole_2010_TFM/cole_tfm_preprint.pdf
Thanks a lot!
C4sh

I think it means temporal aliasing artifacts when rendering lines in animations. They show up as brighter pixels crawling along the line.
Once you know about those, your enjoyment of computer animated movies will decrease significantly. Sorry about. It cannot be undone. :-)

Related

Sound detection of cutting woods

Im really new to machine Learning.I have a project to identify a given sound.(Ex: cutting wood)In the audio clip there will be several sound. What i need to do is recognise that particular sound from it. I red some articles about machine learning. But i still have lack of knowledge where to start this project and also I'm running out of time.
Any help will be really appreciated. Can anyone please tell me how to do this?
Can i directly perform template(algorithms) matching for a sound?
It's a long journey ahead of you and Stack Overflow isn't a good place for asking such a generic question. Consult help section for more.
To get you started, here are some web sites:
Awesome Bioacoustic
Comparative Audio Analysis With Wavenet, MFCCs, UMAP, t-SNE and PCA
Here are two small repos of mine related to audio classification:
Gender classification from audio
Kiwi / not-a-kiwi bird calls detector
They might give you an idea where to start your project. Check the libraries I am using - likely they will be of help to you.

View Interpolation?

Given images from a certain viewpoints is there some software out there which can help me interpolate the views(i.e. Viewpoint interpolation software?).
Thanks,
View Interpolation is an illposed and very difficult problem, which in general has no optimal solution in real world scenarios.
This is because of several reasons, some of which include
Wide Baseline Matching
Disparity Estimation
Occlusion Handling (Folds and Holes)
The quality of the outcome highly depends on your video footage, especially on how close together the cameras are.
Nevertheless, research is ongoing. Dyer and Seitz for example achieved nice results on constrained examples:
http://homes.cs.washington.edu/~seitz/vmorph/vmorph.htm
Stich et.al. from TU Braunschweig showed some amazing results with their Virtual Camera system, which probably is the one thing, you are looking for:
http://www.youtube.com/watch?v=uqKTbyNoaxE
And finally, for soccer enthusiasts:
http://www.youtube.com/watch?v=cUK1UobhCX0
http://www.youtube.com/watch?v=UePrOp2s31c
As a starting point, look for Image Morphing and View Morphing.
If you want, I can provide some more papers on the topic.
Good luck! :)
EDIT: Also, if you're interested, here's my work on Spatial and Temporal Interpolation of Multi-View Image-Sequence.
http://tobiasgurdan.de/research/

Best resources to learn about graphics and imaging?

Having spent a bunch of time recently doing 2D work that involves pixel manipulation of bitmaps and blending/compositing, I've run up against the limits of my own understanding with respect to colorspaces, non-RGB color worlds, etc.
I'd like to go back to basics and learn how all this stuff actually works, so that I'm not shooting in the dark next time I need to think about how to set up a blend function, and I know how to play with color palettes, etc.
Any pointers for good places to start on the path? Online references good, actual books that are clearly written are better. (Not looking for something that's just piles of equations, but can follow mathy stuff if it's not too terse.)
Thanks!
I liked these tutorials:
http://www.student.kuleuven.be/~m0216922/CG/index.html

Graphics/Vision Interesting Topics

I would like to do an interesting project for a computer graphics course. I know that there is a lot of literature out there (i.e. SIGGRAPH conference papers). I have a very large range of interest with regard to computer graphics (i.e. image processing, 3D modeling, rendering, animation). However, I've only taken computer vision/graphics for 2 semesters and thus don't have too much background experience, except for the class projects that I had to do.
I've been looking through SIGGRAPH papers trying to see if there is anything that will be of interest to me but the literature is extremely vast. I was wondering if anyone has any topic suggestions, anything interesting that you ran across that you could recommend. I would prefer to do something fun yet slightly challenging (not really interested in making a shooter game).
If this question does not belong here, I apologize and please let me know where I should move it.
Thanks!
Image Drawing animator. (the name is kind of misleading, but I didn't care much about it)
Anyway, the software does the following:
Takes an image say a JPEG or BMP as input.
Extract the lines from the image. (I used Matlab and Laplace transformations)
Convert the static lines to Vector paths.
Simulate drawing the image using the extracted paths.
In summary, you should give an image, for example a city scape, the program extract all lines and start drawing the buildings, streets and sunset lines, then finally add the colors one by one, until the full image is done.
Real time hand(s) detector.
You'll have plenty of interesting and fun applications with this.

How to implement old film effect?

I'd like to implement an old film effect on pictures. Does anyone know a library or even the rare maths involved? I'd like it to cope with red shift for over-exposition and the rest. Even if you don't know the maths or a library, a pointer to any technical doc will be appreciated.
Clarification: I need to write these routines for a project of my own. I'd like to know what kind of processing has to be done and how. Doesn't matter the environment and system, I just need some hint on how process RGB data
You mention Magic Bullet from Red Giant Software in your comments. There's an impressive amount of image processing know-how behind the development of Magic Bullet. You'd probably have an easier time implementing a host interface for After Effects or Final Cut Pro plug-ins and using Magic Bullet.
If you want to see some source code in action, examine the open source projects that do image processing like GIMP, CinePaint, FreeFrame, etc.
You could try with as3 bitmapdata noise function http://livedocs.adobe.com/flash/9.0/ActionScriptLangRefV3/flash/display/BitmapData.html#noise%28%29
If you can find a plugin for Paint.Net, I'm sure you could just use that dll in your program. Is this the sort of thing you're looking for?
Rare maths?
Create several different transparent PNGs with scratch and dust marks on it. Take a pic, adjust the hue, saturation and brightness (algorithms for this aren't that complex) to fade out the pic, then overlay one to many of the scratchy PNGs. The more scratch/dust PNGs you have, the more random the effect you can create.
Not much math here IMHO.

Resources