CPSC : Data-driven Computer Graphics Jinxiang Chai

Compute Graphics

Traditional Graphics Versus Data-driven Graphics Lighting Geometry Motion texture Surface property

Conceptual world ModelingSimulation Traditional Graphics

Conceptual world ModelingSimulation Traditional Graphics shape modelsreflection models motion models

Conceptual world ModelingSimulation Traditional Graphics

Conceptual world ModelingSimulation Traditional Graphics Pros: + Compact representation + Easy to manipulate Cons: - Very hard to build realistic models - Too complex to simulate

Data-driven Graphics

Real world Data capture Data analysis and synthesis Data-driven Graphics Pros: + High realism + Computer cost independent on the complexity of the model Cons: - Large set of data - Hard to control, edit, modify

What You Will Learn An in-depth study of data-driven computer graphics Learn how to find and formulate a research problem Refine your presentation skill

My Research Interest Interested in animation, graphics, and vision Methods for creating and manipulating high-dimensional visual media (animation, models, images, and videos) Data-driven approach Video-based data capture Thesis: exploiting spatial-temporal constraints for interactive animation control

Thesis Research Goal: everyone can generate and control human animation easily and quickly Online animation control

Thesis Research Goal: everyone can generate and control human animation easily and quickly Online animation control

Thesis Research Goal: everyone can generate and control human animation easily and quickly Offline animation control User input Output animation

Thesis Research Goal: everyone can generate and control human animation easily and quickly Offline animation control User input Output animation

Prerequisites A good working knowledge of C/C++ or Matlab A good understand of math (linear algebra, probability theory ) Background in CG Willing to learn new stuffs (optimization, statistical learning, computer vision, etc.)

Grading Schemes Paper presentation (20%) Class participation/discussion (20%) Paper summary (20%) Final project (40%)

Paper Presentation Before the talk Visit the project webpage Download the video or ask me for the video Give minutes talk Lead the paper discussion Come to my office hours if u need help

Class Participation/Discussion Show up Do the reading Submit the paper summary to me BEFORE the class Actively participate in paper discussion

Final Project Approved by the professor Student can work in a group of two Submit your code and final project report Talk to me if you need any helps Late policy: 20% reduction per day if you do not have good reasons

Grading Schemes Paper presentation (20%) Class participation/discussion (20%) Paper summary (20%) Final project (40%)

Chai ’ s Talk/Paper Style Introduction What? Why? How? Related work or background Algorithm overview Describe each step of the algorithm Experiments & results Discussion & future work

Other Information My My homepage: My office: Rm 527D Bright Office hours: MW 4:00-5:00 Pm Course webpage:

Me Today Your background Graphics? Math? Coding? Your research Interest? Master/Ph.D. (year)? Why do you take this class?