Computational Photography

The course provides a hands on introduction to techniques in computational photography -- the process of digitally recording light and then performing computational manipulations on those measurements to produce an image or other representation. The course includes an introduction to relevant concepts in computer vision and computer graphics. Computational Photography uses computational techniques from computer graphics and computer vision to enhance the process of recording and illustrating both the actual world around us and producing new, creative, imagery. These computational techniques allow recording and reprocessing light in ways that were not possible in traditional photography. This is designed to be an advanced undergraduate course for students who are already familiar with programming and some mathematics including linear algebra. The course will cover the 3 Rs of computational photography: how to record, represent, and render scenes. Popular image-based algorithms will be covered in detail and implemented in a series of practical assignments. Special thanks to Alexei Efros, whose course at CMU was an inspiration for this class. first assignment second assignment Syllabus Jan. 11 lecture 0 (introduction and a little color) Jan. 13 lecture 1 (color and assignment 1, due Wed 20 midnight. (extended to Thursday)) Jan. 20 Continued... Jan. 27 lecture 2. Feb. 1 Continued and lecture 3 (assignment 2 introduced, part 1 due Monday Feb 8.) Feb. 3 lecture 4 (fixed link on assignment 2) Feb. 8 lecture 4 review of formulating gradient domain editing constraints.) Feb. 10 lecture 6. Feb. 15 ice day. Feb. 17 lecture 7. Feb. 22 lecture 8 and make-up class on Planar Homographies (on whiteboard). Feb. 29 Instructor snow day (make-up individual, one-on-one midterms scheduled for next week) Mar. 2 Review planar homographies homework and derivation. Mar. 7 lecture 9 High Dymamic Range Photography (HDR) intro.. Mar. 9 HDR review ... Mar. 28 pinholes and stereo Mar. 30 long panoramas and using matching for recognition ... Apr. 6 Accidental anti-pinholes April 11 How Kinect 1 works April 13 How Kinect 1 works