The goal of this assignment is to give you a sense of what an animation paper is like, and also to get some sense of what people are interested in. It’s also a bit of social engineering to get everyone talking about animation stuff.
Note: you are not supposed to read all the details of the paper. You are just going to read over the front parts, and skim over the rest.
Start by looking over my notes on graphics/animation papers for this class.
Each person will do this exercise for 4/5 papers – I will assign each person 2 papers, and then you will pick 2 more from the list below. When you are looking through the list of the papers at the various conferences (to find ones on the list), see if a paper sticks out that really interests you. If you find one, add it to your list of papers.
4 papers is (intentionally) too many to read. And the papers are probably things that you don’t have the technical background (yet) to understand the details. But the goal is to get you to learn to find the gist quickly, and to see what is interesting to you.
For each paper you look at, you need to:
- Identify “The Sentence.” If you really can’t find it, try to create it yourself. My guess is, that for most SIGGRAPH/SCA papers, you will find “The Sentence.” (note: you should copy the sentence out of the paper, or be explicit that you are making it up – or say where the sentence appears in the paper.)
- State “The Problem”.” Again, the authors should make this easy. But you should be able to state quickly what the problem the paper deals with is. It could very well be that this is really similar to the answer to #1.
- See if you can state the key idea of the paper in a sentence or two. You might not understand the key idea (as it might involve techniques that you don’t know yet).
- Describe what this paper lets you do. This has two parts: first, identify the cool demonstration of what the method does – what is the killer example? (hint: go to the author’s web site and watch the video!). Second: try to figure out what the ideas/techniques in the paper might be good for.
- Did you find any other materials? (videos? talk slides? extra explanations?)
- Did you identify any topics that you would need to understand before you could read this paper more closely? Are there words you don’t know, unfamiliar concepts, other techniques or references that are referred to that you don’t know and feel like your really need to (if you were going to really read the paper).
Note that I did not ask you to write a summary of the paper! In fact, I did not even ask you to read the whole papers. You do need to find the paper (shouldn’t be hard), and look around for some extra information. And write 7 or so sentences (that answer 7 questions – since Q4 has 2 parts). Please use the paper title as the title of your post, be explicit about which part of the post is answering which question, and whether you were assigned the paper, chose it from the list, or chose it despite not being on the list.
I wrote an example for one of the papers for last course (that didn’t include Q7). In fact, you can see all of the student responses to this assignment.
For each paper, write the answers to the questions as forum discussion starter on this forum on Moodle. The assignment is due on Friday, February 8th (to keep the symmetry of assignments due on Friday) – however, assignments will be considered on time, provided that they are all entered into Moodle by 5pm on Sunday, February 10th. I need time to look these over before class on Monday.
Be prepared to talk about the papers that you looked at in class on Monday, February 11th. You might want to print out what you wrote as answers to the questions and bring them with you.
Here is a list of papers chosen from recent conferences. In addition to the two papers you were assigned, you should pick 2 more from this list. You should be able to find the paper on the web (for example, in the ACM Digital Library), but you might also try looking at the “Graphics Papers on the Web” Resource (check this out – you will find it really valuable).
Slight change: rather than assigning papers, I am going to give you a shorter list. You may pick your own 4 from this list. I have made sure that each person has at least one of their “interesting papers” on the list. (OK, one exception where the papers were a little farther from class topics). For your 4, you must pick at least one from each category (and two from one category).
- Falling and landing motion control for character animation
- Eyecatch: simulating visuomotor coordination for object interception
- Optimizing Locomotion Controllers Using Biologically-Based Actuators and Objectives
- Deformable Objects Alive!
- Synthesis of Detailed Hand Manipulations Using Contact Sampling
- RigMesh: automatic rigging for part-based shape modeling and deformation
- DRAPE: DRessing Any PErson
- Efficient Simulation of Example-Based Materials
- Rig-space physics
- Fast Simulation of Skeleton-Driven Deformable Body Characters
- Data-driven Finger Motion Synthesis for Gesturing Characters
- Motion graphs++: a compact generative model for semantic motion analysis and synthesis
- Accurate realtime full-body motion capture using a single depth camera
- Continuous Character Control with Low-Dimensional Embeddings
