Proj 1

Proj 2

Proj 3

maya plugin info

Project 3 - Do Something Cool!

The purpose of this project is for you to do something cool, related to animation. Gvien the short amount of time you have for this project, the amount of implementation you will be able to do may not be all that large, but the idea is that you should have a chance to learn a lot about some topic that we will not get to cover in class.

Since the main goal is for you to learn something about some topic we didn't discuss, part of your task is to identify the topic, identify some of the literature about the topic, and do something to convince me that you've learned something about the topic.

The ground rules are purposely left open. Basically, we can decide what your project will be on an individual basis. Some basic kinds of projects to consider:

  • Pick a paper and build an implementation of it.
  • Pick a topic and write a literature survey of it.
  • Do some kind of demo that combines two ideas from papers you've seen.
  • Pick a problem and try some new solution to it.
  • Pick a method and try it out on some problem it hasn't been applied to.

Ground Rules

There are some ground rules:

  • Your project must be approved by me.
  • Part of your project is to read at least 3 papers related to the subject. 2 of these you must find yourself, and must be approved by me. For these 3 papers, you must write summaries.
  • Your final results must be placed on the web. All writings, any animations you make, all the code, ...
  • The topic must somehow be related to animation. I'm willing to take a pretty broad view of what this means, but I reserve the right to reject any topics I feel are too far afield.
  • You are encouraged (but not required) to work in groups.

The deadlines:

  • Friday, April 12th - You must have met with me to discuss project ideas
  • Wednesday, April 17th - You must send me a paragraph with what your topic is. We will begin a conversation (both by meeting and by email) to evolve the definition of the project.
  • Monday, April 22nd - You must send me a description of your project.
  • Wednesday, April 24th - You must have had your project approved.
  • Monday, April 29th - You must have had your list of papers approved (so you must send me a list ahead of time, in case I reject your list).
  • Friday May 3rd - You must give a status report on your project (unclear if this will be an oral presentation in class or not).
  • Friday May 10th - Final projects due. (University rules prevent me from accepting anything later than this)

In case you're wondering, a third of the 4 weeks is devoted to defining the project. A big part of this is to learn how to define a project, so I have no problem with that.

Some Ideas....

Here are some sample project ideas...

  • Implement Video Textures (from the siggraph paper)
  • Implement Jos fluids (the simple 2D fluids described by Jos Stam in his Siggraph paper)
  • Implement Baraff and Witkin cloth.
  • Implement Pose-space deformations.
  • Particle system crowd simulation (flocks/boids)
  • Non-Photorealistic rendering - make a new style work for animation
  • Paint on video (planar tracking/segmenting, drive image warps, ...)
  • Motion capture processing (robust statistics or optimization, from optical data)
  • Ngo/Simms spacetime/GA based synthesis
  • Walk/Run generator from data
  • Mocap from images
  • Witkin/Kass/Cohen spacetime synthesis
  • quadraped/multiped
  • video de-interlacing
  • autocinematography with occlusions
  • faces driven by video analysis (black & yacoob)
  • map human motion to other characters (furniture)
  • automatic camera control during manipulation or visualization
  • automatically build strobed view (auto-summarization)
  • perlin dancer (synthesis motion via noise)
  • perlin noise to "liven" mocap
  • automatic explanation generation
  • shadow/light matching
  • skin/muscles
  • optimization-based keyframe interpolation (with avoidance)
  • automatic exageration/cartoonification of motion
  • non rigid figure tracking to drive animatiom parameters (visual servoing)
  • Thin-plate-spline image warps with constraints.
  • cycle analysis
  • automatic constraint detection
  • Modal dynamics
  • Caltech Dynamic Splines
  • Quaternion interpolation splines integrated into spacetime...
Motion Childification
Use neuro-anatomy-based ideas on how children have less control of their muscles (and therefore have jerkier motions and less accuracy).
Motion Level-of-Detail
Simplify motions (to both simpler characters and less temporal resolution) for when the character is too small to be worth animating in full detail.
Optical Mocap Processor
Convert marker position information into skeletal motion data.
Automatic Skeleton Parameter Finder
Fit the limb lengths of a skeleton to a 3D "skin" such as a mesh.
Facial Motion Capture
Use Prof. Green's system to make some animation. Specifically, demonstrate his data of babies on an adult (or vice-versa).
Colored Pencil Renderer
Render images in the style of colored pencil drawings. Make animations of this (such as the style of Bill Plympton).
Cyclic Motion Creator
Turn periodic motions into infinite (but not exactly repetitive) cycles.
Implement Motion Editing in Maya
Re-create the Lee & Shin method (or a variant thereof) using the IK solver and other tools inside of Maya (or some other commercial package)
Cartoon Output
Write a "renderer" that takes 3D animation and produces a 2D cartoon (preferably in a standard file format such as flash).
Dynamic Timewarping
Implement dynamic timewarping and use it to automatically create transitions or blends.
Move the "skin" of a character in response to the movement of its skelleton. Implement this in some cool way that is interesting.
Create animation (2D or 3D) based on real video input. Build a tool for making this (at least semi-) automatic.
Motion Mapping
Map motion capture data to non-human characters.
Automatic Filmmaking
Automatically create animations from motion capture data. This should include automatic camera and lighting control, automatic geometry setup.


website (c) 2002, Michael L. Gleicher