InfoCoBuild

ECSE 6969 - Computer Vision for Visual Effects

ECSE 6969: Computer Vision for Visual Effects (Spring 2014, Rensselaer Polytechnic Institute). Instructor: Professor Richard Radke. The course emphasizes research topics that underlie the advanced visual effects that are becoming increasingly common in commercials, music videos and movies. Topics include classical computer vision algorithms used on a regular basis in Hollywood (such as blue-screen matting, structure from motion, optical flow, and feature tracking) and exciting recent developments that form the basis for future effects (such as natural image matting, multi-image compositing, image retargeting, and view synthesis). We also discuss the technologies behind motion capture and three-dimensional data acquisition. Analysis of behind-the-scenes videos and in-depth interviews with Hollywood visual effects artists tie the mathematical concepts to real-world filmmaking.

Image: ECSE 6969: Computer Vision for Visual Effects


Lecture 01 - Overview of Computer Vision and Visual Effects
Lecture 02 - Bluescreen and Bayesian Matting
Lecture 03 - Closed-form Matting
Lecture 04 - Markov Random Field (MRF) and Random Walk Matting
Lecture 05 - Graph Cut Segmentation, Video Matting, and Matting Extensions
Lecture 06 - Multiresolution Blending and Poisson Image Editing
Lecture 07 - Photomontage and Image Inpainting
Lecture 08 - Image Retargeting and Recompositing
Lecture 09 - Feature Detectors
Lecture 10 - Feature Descriptors
Lecture 11 - Feature Evaluation and Use
Lecture 12 - Parametric Transformations and Scattered Data Interpolation
Lecture 13 - Optical Flow
Lecture 14 - Epipolar Geometry
Lecture 15 - Stereo Correspondence
Lecture 16 - Video Matching, Morphing, and View Synthesis
Lecture 17 - Image Formation and Single-camera Calibration
Lecture 18 - Stereo Rig Calibration and Projective Reconstruction
Lecture 19 - Euclidean Reconstruction and Bundle Adjustment
Lecture 20 - Motion Capture Setup and Forward Kinematics
Lecture 21 - Inverse Kinematics and Motion Editing
Lecture 22 - Facial and Markerless Motion Capture
Lecture 23 - LiDAR and Time-of-Flight Sensing
Lecture 24 - Structured Light Scanning
Lecture 25 - Multiview Stereo
Lecture 26 - 3D Features and Registration

References
Computer Vision for Visual Effects, Spring 2014
Instructor: Richard Radke. These lectures were recorded from Spring 2014's offering of ECSE-6969 at Rensselaer Polytechnic Institute. They accompany my textbook Computer Vision for Visual Effects, published by Cambridge University Press in Fall 2012.