What Makes a Great Picture?15-463: Computational PhotographyAlexei Efros, CMU, Fall 2008© Robert Doisneau, 1955With many slides from Yan Ke, as annotated by Tamara BergPhotography 101• Composition•Framing• Rule of Thirds• Leading Lines• Textures and Patterns•Lighting• Direction• Color coordination / balance•“Golden Hour”Framing“Photography is all about framing. We see a subject --and we put a frame around it. Essentially, that is photography when all is said and done.”-- from photo.blorge.comFrame serves several purpouses:1. It gives the image depth2. Use correctly, framing can draw the eye of the viewer of an interest to a particular part of the scene. 3. Framing can bring a sense of organization or containment to an image. 4. Framing can add context to a shot. http://digital-photography-school.com/blog/frame-your-images/Examples of nice framinghttp://flickr.com/photos/paulosacramento/226545698/http://flickr.com/photos/chrisbeach/13868545/http://flickr.com/photos/74531485@N00/929270814/http://flickr.com/photos/freakdog/223117229/http://flickr.com/photos/cdm/253805482/Rules of Thirdshttp://www.photo96.com/blog/?p=371Other examplesMore examplesComplementary colors (of opposite hue on color wheel)Photography 101• Composition•Framing• Rule of Thirds• Leading Lines• Textures and Patterns•Lighting• Direction• Color coordination / balanceI am a sucky photographer……but I am a pretty good photo critic!http://flickr.com/photos/aaefros/# of my Paris photos on Flickr: 32Total # of my Paris photos: ~1250~2%The Postmodern PhotographerThe Old Days: a pre-process• Load film• Find subject• Position camera• Set all the settings “just right”• Take a deep breath…• ...Press buttom!The New Digital Days: a post-process• Get a 2 GB memory cartridge• Take pictures like there is no tomorrow!!!•…• Back home, spend hours of agony trying to find 1-2 good onesHow to recognize the good photos?Y. Ke, X. Tang, and F. Jing. The Design of High-Level Features for Photo Quality Assessment. CVPR 2006.Not considering semantic measures of what makes a photo good (subject matter, humor, etc). Professional = those you would frame, snapshot = those that would stay in photo album.ApplicationsImage search for improved quality along with relevance.Automatically select the best photos from a set of vacation pictures to choose the best ones to show.See if computer can perform well on a traditionally human task.Prof - Obvious what one should be looking at ie easy to separate subject from the background. Snap – unstructured, busy, filled with clutter.Abstract concepts - “Good composition, color & lighting”- Snaps – entire photo blurry indicates poor technique. Prof - background out of focus by widening the lens aperture, but foreground in sharp focus.Make the subject pop out by choosing complementary colors for subject & background. Isolate the subject by increasing lighting contrast between subject & background.(Sur)Snaps look real, while prof photos look surreal.(Sur)TechniquesLighting conditions – time of day (morning, dusk), colored filters to adjust color balance (make sky bluer, sunset more brilliant), careful color selection of sceneCamera settings – adjust settings like focal length, aperture, shutter speeds to modify mood, perspective. Eg might use long shutter speed to capture waterfall and give a misty lookSubject matter – ordinary objects in unusual poses or settings (challenging since would need obj rec first)Trying to capture a photo’s “simplicity”More edges near border due to background clutterMore edges near center of imgMean Laplacian of snapshots Mean Laplacian of professional Expect high quality photos to have high spatial frequency edges nearer to center than snapshots More uniformly distributedMore concentratedEdge widthCalculate area that edges occupy – width of bounding box covering 96% of edge energyCluttered regions should tend to produce a larger bounding box, and well defined subjects should produce a smaller one..94.56For query image find k nearest neighbors in training set. Quality = number of profneighbors in top 5.# unique hues smaller for prof photos even though they tend to look more vibrant and colorful (S,V may vary more) –another measure related to “simplicity”20 bin histogram defining possible unique huesMost unlikely colors…From Lalonde and Efros, ICCV’2007Prof photos should have some part of photo in sharp focusProf photos usually have higher contrastContrast = width of middle 98% mass of histContrastProfessional photographers may adjust exposure to be correct on subject only so subj pops from bkd. Cameras tend to adjust brightness to average at 50% gray, but prof photos might deviate significantly. Use ave brightness as feature.Use photos average rating as ground truth quality measureUse only top 10%, bottom 10% as dataset.Use half for training/half for testing. Photo contest website, user rated72% classification rateWrap Up© Robert BrownLooking back…1. Why we were here?2. What did we learn?3. How is this useful?Our Goal: The Plenoptic FunctionFigure by Leonard McMillanOur Tools: The “Theatre Workshop” Metaphordesired image(Adelson & Pentland,1996)Painter Lighting DesignerSheet-metalworkerPainter (images)Lighting Designer (environment maps)Sheet-metal Worker (geometry)[Szeliski & Kang ‘95]depth map 3D rendering… working togetherHow is this useful?1. You learned a basic set of image-based techniques• All quite simple• Most can be done “at home”2. You have your digital camera3. You have your imaginationGo off and explore!THANK
View Full Document