Digital Photography with Flash and No-Flash Image Pairs By: Georg PetschniggManeesh Agrawala Hugues HoppeRichard Szeliski Michael CohenKentaro Toyama,

Slides:



Advertisements
Similar presentations
網 上 相 簿 工 作 坊. Imaging Filters What is PhotoRite? Advanced image processing technology for automatic photo enhancement. Just ONE Click to Enhance! Everyone.
Advertisements

Digital Photography I Photography I Aperture ISO Shutter Speed.
Manual Camera Settings
ISO, Aperture and Shutter Speed For Beginners. The photographer can control how much natural light reaches the sensor by adjusting the camera's ISO shutter.
Exposure The balance of the amount of light allowed entering the photographic medium There are 3 elements used to create the desired exposure 1. ISO 2.
Spatial Filtering (Chapter 3)
EDGE DETECTION ARCHANA IYER AADHAR AUTHENTICATION.
Lightning Lesson Digital Imagery & Film Exposure The balance of the amount of light allowed entering the photographic medium There are 3 elements used.
December 5, 2013Computer Vision Lecture 20: Hidden Markov Models/Depth 1 Stereo Vision Due to the limited resolution of images, increasing the baseline.
1 Automatic Compensation for Camera Settings for Images Taken under Different Illuminants Cheng Lu and Mark S. Drew Simon Fraser University {clu,
Photography (the very basics). Before we get started… - These are only very simple explanations - I could be wrong! - Mainly aimed at digital users.
Computational Photography
Lecture 1: Images and image filtering
Segmentation (Section 10.2)
SUSAN: structure-preserving noise reduction EE264: Image Processing Final Presentation by Luke Johnson 6/7/2007.
Announcements Kevin Matzen office hours – Tuesday 4-5pm, Thursday 2-3pm, Upson 317 TA: Yin Lou Course lab: Upson 317 – Card access will be setup soon Course.
Lecture 2: Image filtering
A Novel 2D To 3D Image Technique Based On Object- Oriented Conversion.
© Tracey Garvey Photography
Advanced Digital Photography. Introductions Who Why What.
Capturing and controlling digital images. Great images are not made by digital cameras. They are made by photographers who understand what to look for.
MEMS Photography - or - How to coax pretty images out of a point and shoot camera - with - Brandon & Chris.
Digital Camera Settings
Noise Estimation from a Single Image Ce Liu William T. FreemanRichard Szeliski Sing Bing Kang.
Camera Functions Using Your Digital Camera. 1. What happens when you press the shutter button down halfway? What does macro mode allow you to do? Pressing.
Joel Willis. Photography = Capturing Light Best Light Sources and Directions Basics: Aperture, Shutter Speed, ISO, Focal Length, White Balance Intro to.
A Gentle Introduction to Bilateral Filtering and its Applications 08/10: Applications: Advanced uses of Bilateral Filters Jack Tumblin – EECS, Northwestern.
Automatic Compensation for Camera Settings for Images Taken under Different Illuminants School of Electrical Engineering and Computer Science Kyungpook.
Applying Colour Theory to Visual Design.  Color Theory is the art of mixing colors to achieve desired effects.  The way colors are combined can be used.
Image-Based Rendering from a Single Image Kim Sang Hoon Samuel Boivin – Andre Gagalowicz INRIA.
How A Camera Works Image Sensor Shutter Mirror Lens.
Controlling the Photographic Process. With today’s modern digital cameras you can have as much or as little control over the picture taking process as.
FRITZ SCHNEIDERPEACHAM CYBERNETICS Introduction To Digital Photography II – Camera Features.
Astrophotography The Basics. Image Capture Devices Digital Compact cameras Webcams Digital SLR cameras Astronomical CCD cameras.
03/05/03© 2003 University of Wisconsin Last Time Tone Reproduction If you don’t use perceptual info, some people call it contrast reduction.
AdeptSight Image Processing Tools Lee Haney January 21, 2010.
 The image that the digital camera sensor captures is based on the light reflected or emitted from a subject and how much the sensor is exposed to that.
Why is computer vision difficult?
Digital Photography with Flash and No-Flash Image Pairs Gabriela Martínez Processamento de Imagem IMPA.
11/23/2015On Camera Flash1 Basic Photography Using Flash.
Intelligent Vision Systems ENT 496 Image Filtering and Enhancement Hema C.R. Lecture 4.
REVIEW OF PHOTO TERMS & INTRODUCTION TO DSLR CAMERA MODES PHOTO 2 - 8/20/13 [A DAY]
Skills talk I: Making pictures rather than taking pictures. Bringing faith to life through the power of image.
Tone mapping Digital Visual Effects, Spring 2007 Yung-Yu Chuang 2007/3/13 with slides by Fredo Durand, and Alexei Efros.
U Fast Shutter Speed = Stops the Action u Slow Shutter Speed = Blurs the Action (Dragging the shutter) 1/6th 1/500th Photography Basics u Aperture and.
Instructor: Mircea Nicolescu Lecture 5 CS 485 / 685 Computer Vision.
Chapter 24: Perception April 20, Introduction Emphasis on vision Feature extraction approach Model-based approach –S stimulus –W world –f,
Modern Art - Photography How to pro in photography Instructor: Stanley Ziwei Su.
Lecture 1: Images and image filtering CS4670/5670: Intro to Computer Vision Noah Snavely Hybrid Images, Oliva et al.,
Non-linear filtering Example: Median filter Replaces pixel value by median value over neighborhood Generates no new gray levels.
Quality Enhancement Video Quality. Introduction ● This section will bring you through the following concepts: 1. How lighting and camera positioning enhance.
Digital Cameras in the Classroom Day One Basics Ann Howden UEN Professional Development
CAMERAS, PARTS of the CAMERA, and ACCESSORIES (TAKE NOTES ON THE UNDERLINED MATERIAL AND LABELLED DIAGRAMS)
Heechul Han and Kwanghoon Sohn
Photography (the very basics).
Exposure Control Exposure = Intensity of Light (X) Amount of Time
Year 10 GCSE Scheme of work
Yearbook/Photography Grade 9 Milroy
Vision Basics Lighting I. Vision Basics Lighting I.
Photography (the very basics).
ECE 692 – Advanced Topics in Computer Vision
Rogerio Feris 1, Ramesh Raskar 2, Matthew Turk 1
Introduction to Digital Photography
Chapter IV, Introduction to Digital Imaging: Lesson III Understanding the Components of Image Quality
D40 ISO Experiment.
Digital Visual Effects, Spring 2006 Yung-Yu Chuang 2006/3/8
Camera Basics Digital Photography.
Introduction to Digital Photography
Lecture 2: Image filtering
Shape from Shading and Texture
Presentation transcript:

Digital Photography with Flash and No-Flash Image Pairs By: Georg PetschniggManeesh Agrawala Hugues HoppeRichard Szeliski Michael CohenKentaro Toyama, Microsoft Corporation Presented by: Yael Amsterdamer Advanced Topics in Visual Computing, Spring 2012

The Dilemma: to Flash or not to flash? 2Digital Photography with Flash and No-Flash Image Pairs Natural lighting Low signal-to-noise ratio (SNR) Loss of details Longer exposure – motion blur Harsh, unnatural lighting High SNR More details May cause unwanted artifacts (red eye, shadows, specularities)

Why not both? The idea: use the good features of each photo to create a better image 3Digital Photography with Flash and No-Flash Image Pairs

Other works on combining images 4Digital Photography with Flash and No-Flash Image Pairs Different exposures Panoramic view Relighting Current work handles 2 images with specific characteristics, Envisioned for camera firmware Current work handles 2 images with specific characteristics, Envisioned for camera firmware

Different Applications Denoising Detail transfer – Side requirement: handling flash induced shadows and specularities White Balancing Continuous Flash Adjustment Red Eye Removal 5Digital Photography with Flash and No-Flash Image Pairs

Camera Adjustment to light A certain amount of light is needed for a photo Taking pictures of a dark scene – Increasing exposure time – Opening the aperture – Increasing ISO (sensor sensitivity) The problem – high ISO  noise affects high-frequency details 6Digital Photography with Flash and No-Flash Image Pairs

The Input F – the photo with flash A – the no-flash (ambient) photo – Composed of 3 RGB intensity values for each pixel – A p – one pixel in A Same camera position, focus, aperture – Otherwise, registration is required Adjusted ISO and exposure time Undergo non-linear tone-mapping operations 7Digital Photography with Flash and No-Flash Image Pairs

1st Application: Denoising A classic problem in image processing – The target: analytically reduce SNR One type of solution: smoothing filters Bilateral Filter [Tomasi and Manduchi 1998] – Fast, non-iterative – Averaging close-by pixels – Low-pass filter, combined with – Edge-stopping function 8Digital Photography with Flash and No-Flash Image Pairs

Bilateral filter However, results still have noise or blur (or both) 9Digital Photography with Flash and No-Flash Image Pairs ambient flash Bilateral filter

Improvement: Joint Bilateral Filter In the flash image there are much more details Why not use F to find edges? 10Digital Photography with Flash and No-Flash Image Pairs Bilateral filter Joint Bilateral filter The difference

Not all edges are real … May cause over- or under-blur in joint bilateral filter We need to eliminate their effect 11Digital Photography with Flash and No-Flash Image Pairs

Detecting shadows Observation: the pixels in the flash shadow should be similar to the ambient image Not identical: – Noise – Inter-reflected flash Compute a shadow mask Take pixel p if is manually adjusted Mask is smoothed and dilated 12Digital Photography with Flash and No-Flash Image Pairs Pixels for which we will not use F

Detecting specularities Take pixels where sensor input is close to maximum (very bright) – Over fixed threshold Create a specularity mask Also smoothed and dilated M – the combination of shadow and specularity masks – Where M p =1, we use A Base. For other pixels we use A NR. 13Digital Photography with Flash and No-Flash Image Pairs

There is so much denoising can do It cannot add details missing in the ambient image Exist in flash image because of high SNR We use a quotient image: Multiply with A NR to add the details Masked in the same way 14Digital Photography with Flash and No-Flash Image Pairs Bilateral filtered Reduces the effect of noise in F

Unified process Denoising + detail transfer + masking shadows and specularities 15Digital Photography with Flash and No-Flash Image Pairs

More examples 16Digital Photography with Flash and No-Flash Image Pairs

The opposite of preserving the atmosphere The goal: simulate white light in the scene – What color is the light in the scene? Flash image can help us: The difference between F and A is only the flash light Assume it is proportional to the surface albedo – Inherent property of the surface – Assume the surface reflects light in the same color (will not work for plastic, glass…) 17Digital Photography with Flash and No-Flash Image Pairs

Computing the ambient light We cancel the color of the surface The average c of C p(col) for pixels with certain properties is the ambient light color Then we scale A to cancel the ambient light 18Digital Photography with Flash and No-Flash Image Pairs

Example 19Digital Photography with Flash and No-Flash Image Pairs Estimated ambient light Computed color Ambient original White- balanced

Combining flash and no-flash images Providing complementary details about the scene Use for denoising and detail transfer Use for white balancing Future work – More robustness – Automatization of configuration 20Digital Photography with Flash and No-Flash Image Pairs

Thank you!