Assignment 3, From texts, and/or images to animation videos, Computer Vision,
2018
Due: 11:59pm, 31/5/18
Javen Shi
The University of Adelaide
South Australia
Abstract
The third assignment is about generating animation
videos using texts and/or images. The submission will take
the form. of a conference paper.
1. Introduction
The aim of this paper is to automate some of the anima-
tion production process. If you do not know the animation
production process, google it. You need to explain the ap-
plication, review the related work, and motivate the choice
of your method here. The following questions may get you
started, but you do not have to tackle all of them.
An animation video consists of a number of frames.
Each frame. is an image. If you only use a subset of the
frames/images as key frames, how do you recover the ani-
mation video using algorithms? For example, a video may
have 15 frames per second. If you only use 5 frames per
second, how do you recover the other 10 frames?
If you are given a storyboard of an animation, how do
you generate an animation video using algorithms?
If you are given a movie script. (texts), how do you turn
it to an animation video using algorithms?
2. The method
2.1. Implementation
In order to be able to test the method you will need to
implement it. Fortunately this is made significantly easier
by the fact there are many existing implementations avail-
able. The choice of language, platform, compiler, IDE, and
similar is up to you.
3. Submission
The submission takes the form. of a conference paper,
your code, and a demo video. Please submit a single zip file
(compression) via myuni assignment submission interface.
In the zip file, please use three folders ’Report’, ’Code’,
and ’Video’. Place your report pdf file only in the ’Report’
folder, and place your code in the folder ’Code’. Provide
a README.txt file in the ’Code’ folder to explain how
to use your code (such as downloadinginstalling some
packages, execution of your code). Do not put large pack-
ages/libraries in ’Code’. Use README.txt to explain how
to get packages/libraries. Place a short demo video in the
folder ’Video’ in mp4 format. If the video is too big to up-
load to myuni, upload to youtube and provide the youtube
link in a text file videolink.txt in the folder of ’Video’. Keep
the submission light.
You need to write a paper such as might be submitted to
a conference, and specifically a paper such as might be sub-
mitted to CVPR[1], which is one of the best conferences in
Computer Vision. The paper must be in the CVPR format,
and submitted as a pdf document. By far the easiest way to
achieve that is to use LATEX. LATEXis a very powerful docu-
ment formatting package, it’s free, and it is the only way to
generate well formatted documents that contain maths. It’s
also the easiest way to generate well formatted documents
in general.
All the information about the CVPR paper format is
available on their web site[1]. The paper must be all your
own work, with no text copied from any other document.
The purpose of the paper is to demonstrate that you un-
derstand the problem, and the solution. This means that
your submission should have sections which broadly cover
the following
An introduction, which describes the problem, and the
method
A background section which describes competing ap-
1
proaches to the problem. Achieving this requires that
you understand what the competing approaches do,
how they do it, their advantages and shortcomings, and
how they compare to the current approach. The meth-
ods you compare against here may well perform. better
than the method you are describing. The idea of this
section is not that you show that yours is necessarily
the best method available, but rather that you show that
you understand enough about the literature in the area
to be able to put it in context.
A description of your hypothesis. This will typically
require explaining some part of the algorithm in detail,
and providing examples illustrating its effects and de-
ficiencies. If you propose an improvement then you
should describe how your method works, in enough
detail that a reasonably skilled person would be able to
implement it.
Experimental Analysis. Describe the tests you have
run, and your motivation for having run them. Re-
port the results of the tests and the conclusions that
you have drawn. Again, the goal is not to show that
your method outperforms all comparators, but rather
that you understand what your method aims to achieve,
and can devise, execute, and report upon a set of tests
which demonstrate whether it does so. If you have im-
proved upon the base method then you have an oppor-
tunity here to show that your improvement is well mo-
tivated, and possibly even that it works.
Conclusion. Demonstrate that you have learned some-
thing worthwhile from the process, possibly including
ideas about what you might do to improve the method
you are reporting on.
The paper you submit must be in the format specified
for CVPR 2017, which is specified as part of the author
instructions[1]. The easiest way to achieve this is to down-
load the LATEXtemplate and use that. You can use some other
means if you really want to, but your paper needs to con-
form. to the CVPR style. specification. The only exception
is that I don’t mind if you use a4 paper rather than their
preference for letter paper (it’s a US conference).
Good paper exemplars? Go to the CVPR websites (not
limited to 2017), and read the BEST PAPER AWARD pa-
pers and the oral papers in the past. You may not fully un-
derstand the the papers, but they should give you some idea
what a look paper should look like.
CVPR papers are up to 8 pages, and most of them are 8
pages. As for the assignment, it is limited to maximally
8 pages too, and there is no minimum page requirement
(as we adopt CVPR requirement). If you can impress us
positively with only 1 page, that is great. Though I think
putting everything beautifully in one page is much harder
than putting them in more pages. We will not be marking
the quality of your code, only checking that it shows enough
evidence that you wrote it yourself. We will mark the qual-
ity of the demo video.
4. Assessment
Your submission will be assessed primary in terms of
how well it demonstrates that you
understand the problem,
have come up with a sensible hypothesis
can design and implement a suitable set of tests which
will demonstrate (or disprove),
can interpret the results of these tests, and draw a sen-
sible conclusion.
Your submission will be assessed in terms of the demo
video too. Do not forget to produce a demo video.
We will not be marking the quality of your code, only
checking that it shows enough evidence that you wrote it
yourself.
5. Conclusion
If you have questions, please ask them on the forum, as
they are likely to be of interest to others also. It is impor-
tant to check the forum for the latest information about the
assignment too.
References
[1] CVPR. Ieee computer society conference on computer vi-
sion and pattern recognition. See http://cvpr2017.
thecvf.com/.