Appearance Models for Graphics COMS 6998-3, Lecture 1 Ravi Ramamoorthi.
Post on 21-Dec-2015
223 Views
Preview:
Transcript
• This course mainly focuses on materials• But appearance depends on geometry, materials, lights
Computer Graphics Rendering
Geometry
Lighting
Materials
Rendering
ViewpointCamera
Image
Photorealistic Rendering
Materials/Lighting(Texture Reflectance[BRDF] Lighting)
Realistic input models required
Arnold Renderer: Marcos Fajardo
Rendering Algorithm
80’s,90’s: Physically based
Geometry
70’s, 80’s: Splines90’s: Range Data
Computer Vision Analysis
• Most algorithms assume very simple lighting, materials
Image
Lighting
Materials
Vision alg.
ViewpointCamera
Geometry
Inverse Rendering
Geometry Inverse Rend
ViewpointCamera
Lighting
• Useful for acquiring material models in graphics• Recognizing materials in vision
Materials
Material Recognition
Photographs of 4 spheres in 3 different
lighting conditions
courtesy Dror and Adelson
Complex materials
• Geometry, illumination, reflectance all important• Often scales of geometry: Continuum of geometry/reflectance
Appearance important other areas
• Physics• Materials science• Cosmetics• Building materials• Car paints• Textiles• ArtUsing computer, complex simulations doable
Topics
• Modeling how light interacts with matter
• Measurement/acquisition of materials
• Image-based modeling and rendering
• Analytic methods
• Real-time rendering
• Focus mainly on computational methods
Outline
• Why appearance models?
• Examples of recent graphics images
• Approaches: Physical, structural, phenomenological methods
• Overview of course logistics
Approaches
• Physical: Understand basic physics
• Structural: Understand microstructure (patinas, fabrics, layered models)
• Phenomenological: Empirical
Physical example: Fresnel• Dielectrics: Increasing specularities grazing angles
• Metals: reflection changes with wavelength
Copper-colored Cook-Torrance
Phenomenological Models
• Lambertian:
• Phong:– Really corresponds to extended light source
• Also, gaussian surfaces, splines, wavelets, Zernike polynomials, spherical harmonics, …
• BRDF itself phenomenological model
cos iB L
s s
v LB R L R V
Course Goals, Format
• Goal: Background and current research on appearance models in graphics and vision
Course Goals, Format
• Goal: Background and current research on appearance models in graphics and vision
• Columbia is the best place for this!!
Course Goals, Format
• Goal: Background and current research on appearance models in graphics and vision
• Columbia is the best place for this!!
• Format: Alternate lectures, student presentations of papers
• http://www.cs.columbia.edu/~ravir/6998/
Course Logistics
• No textbooks. Required readings are papers available online (except 3 handouts today)
• Office hours: before class. My contact info is on my webpage: http://www.cs.columbia.edu/~ravir
• Will (almost certainly) count for PhD elective breadth in graphics/HCI (if taken on grades)
Requirements
• Pass-Fail– Show up to class regularly– Present 1 (maybe 2) paper(s)– Prefer you do this rather than just sit in
• Grades– Attend class, participate in discussions (10%)– Present 2 (maybe 3) papers (30%)– Project (60%)
Project
• Wide flexibility if related to course (some ideas off main course webpage). Can be done in groups of 2-3– Implementation/extension of one of the papers
– Modeling of challenging natural object
– Theoretical analysis/extension/verification
– Best projects will go beyond simple implementation (try something new, some extensions)
• Alternative (less desirable): Summary of 3 or more papers in an area– Best projects will explore links/framework not discussed by
authors, and suggest future research directions
Prerequisites
• Strong interest in graphics (and vision)• Computer graphics experience (4160)
– What if lacking prerequisites? Next slide
• Course will move quickly– Covering recent and current active research
– Some material quite technical
– Assume some basic knowledge
– Many topics. Needn’t fully follow each one, but doing so will be most rewarding.
If in doubt/Lack prerequisites
• Material is deep, not broad– May be able to pick up background quickly– Course requirements need you to really fully
understand only one/two areas (topics)– But if completely lost, won’t be much fun
• If in doubt, see if you can more or less follow some of papers after background reading
• Ultimately, your call
Assignment this week
• E-mail me (ravir@cs)– Name, e-mail, status (Senior, PhD etc.)
– Will you be taking course grades or P/F
– Background in graphics/any special comments
– Optional: Papers you’d like to present FCFS
• Paper presenters for next week [You (may) get a one-paper reduction in load]– Oren-Nayar, Torrance-Sparrow, Koenderink-van Doorn
top related