Completed
Background: BRDF
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Physically-Motivated Learning of Shape, Material and Lighting in Complex Scenes
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Image Formation is a Complex Process
- 3 Component Problems of Inverse Rendering
- 4 Ambiguities of Inverse Rendering
- 5 Approaches to Inverse Rendering
- 6 A Canonical Challenge in Inverse Rendering
- 7 Outline
- 8 Image Formation: Rendering Equation
- 9 Background: BRDF
- 10 Background: Lighting
- 11 Large-Scale Dataset of Complex Materials
- 12 Physically-Based Rendering Layer
- 13 An Example
- 14 Comparison with Other Methods
- 15 Generalization to Real Data
- 16 Single Image Inverse Rendering
- 17 Physically Motivated Network: Rendering Layer
- 18 Synthetic Experiment: Global Illumination
- 19 Physically Motivated Network: Cascade Structure
- 20 Example: Cascade Structure
- 21 Example: Shape and Material Estimation
- 22 Example: View Synthesis
- 23 High-Quality, Photorealistic Augmented Reality
- 24 Key New Challenge: Spatially-Varying Lighting
- 25 Lighting Estimation Methods
- 26 Inverse Rendering in Indoor Scenes: Challenges
- 27 Ground Truth for Inverse Rendering Is Non-Trivial
- 28 Comparisons of Rendered Images
- 29 Compact and Effective Physical Lighting Representation
- 30 Spatially Varying Lighting Estimation: Representation
- 31 Physically-Motivated Network for Indoor Scenes
- 32 Spatially Varying Lighting Estimation: Results
- 33 Inverse Rendering in Real Indoor Scenes
- 34 Inverse Rendering: Quantitative Results
- 35 Object Insertion with Single Unconstrained Image
- 36 Object Insertion: User Studies
- 37 Material Editing with Single Unconstrained Image
- 38 Lightweight Acquisition with a Mobile Phone Camera
- 39 Physically-Motivated Deep Network
- 40 Conclusions
