Correcting Over-Exposure in Photographs

Slides:



Advertisements
Similar presentations
SOFT SCISSORS: AN INTERACTIVE TOOL FOR REALTIME HIGH QUALITY MATTING International Conference on Computer Graphics and Interactive Techniques ACM SIGGRAPH.
Advertisements

High Dynamic Range Imaging Samu Kemppainen VBM02S.
Purpose of this Session Optimizing tonality. Is zone system still relevant? How digital photography changed the game. Considerations for a “fine art”
1School of CS&Eng The Hebrew University
Image Matting with the Matting Laplacian
Nathan Johnson1 Background Subtraction Various Methods for Different Inputs.
Shaojie Zhuo, Dong Guo, Terence Sim School of Computing, National University of Singapore CVPR2010 Reporter: 周 澄 (A.J.) 01/16/2011 Key words: image deblur,
Artifact-free High Dynamic Range Imaging Orazio Gallo UC, Santa Cruz Natasha Gelfand, Wei-Chao Chen, Marius Tico, and Kari Pulli Nokia Research Center,
Image Compositing and Matting. Introduction Matting and compositing are important operations in the production of special effects. These techniques enable.
Image Matting and Its Applications Chen-Yu Tseng Advisor: Sheng-Jyh Wang
Effective Image Database Search via Dimensionality Reduction Anders Bjorholm Dahl and Henrik Aanæs IEEE Computer Society Conference on Computer Vision.
Computational Photography Prof. Feng Liu Spring /15/2015.
Machine Learning Case study. What is ML ?  The goal of machine learning is to build computer systems that can adapt and learn from their experience.”
Digital Image Processing Ligang Liu Zhejiang University
A Closed Form Solution to Natural Image Matting
Image Forgery Detection by Gamma Correction Differences.
Single Image Haze Removal Using Dark Channel Prior Professor : 王聖智 教授 Student : 戴玉書 CVPR Best Paper AwardBest Paper Award Kaiming HeKaiming He, Dept.
1 Photographic Tone Reproduction for Digital Images Brandon Lloyd COMP238 October 2002.
Dynamic Range Compression & Color Constancy Democritus University of Thrace
LOCUS Demo Stefan Zickler. Two “different” classes Class “Car Side Views” Class “Car Rears”
Gradient Domain High Dynamic Range Compression
A quick introduction to shooting digital images in RAW.
1.  Introduction  Gaussian and Laplacian pyramid  Application Salient region detection Edge-aware image processing  Conclusion  Reference 2.
PG 2011 Pacific Graphics 2011 The 19th Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2011) will be held on September 21 to.
Tone mapping with slides by Fredo Durand, and Alexei Efros Digital Image Synthesis Yung-Yu Chuang 11/08/2005.
Joint Histogram Based Cost Aggregation For Stereo Matching Dongbo Min, Member, IEEE, Jiangbo Lu, Member, IEEE, Minh N. Do, Senior Member, IEEE IEEE TRANSACTION.
Goals of Computer Vision To make useful decisions based on sensed images To construct 3D structure from 2D images.
High dynamic range imaging. Camera pipeline 12 bits8 bits.
G52IIP, School of Computer Science, University of Nottingham What we will learn … Topics relate to the use of computer to Acquire/generate Process/manipulate/store.
Image-Based Rendering from a Single Image Kim Sang Hoon Samuel Boivin – Andre Gagalowicz INRIA.
High Dynamic Range (HDR) Photography. Camera vs Eye Eye sees a wider range of color luminance than digital cameras HDR’s images compensate for this by.
Anderson VMC DPH31G. Histograms are a graphic representations (a picture) of the tonal value for each pixel in your photo. The horizontal axis of the.
Tone Mapping Software Photomatix Pro Application to Photography Konferenz und Workshop '05 Reality-Based Visualization.
 Is the technique of taking several shots of the same subject using different aperture, shutter speed or ISO settings  Why do you think you would want.
Exposure Bracketing: Taking 2 or more photographs of the same scene, at different exposures; #1- according to light meter #2- one/two stops underexposed.
G52IVG, School of Computer Science, University of Nottingham 1 Administrivia Timetable Lectures, Friday 14:00 – 16:00 Labs, Friday 17:00 -18:00 Assessment.
1 Digital Image Processing Dr. Saad M. Saad Darwish Associate Prof. of computer science.
Digital Photography Basics Light Metering White Balance RAW vs. JPEG Resolution & Megapixels Camera Settings.
 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.
How digital cameras work The Exposure The big difference between traditional film cameras and digital cameras is how they capture the image. Instead of.
Improving Image Matting using Comprehensive Sampling Sets CVPR2013 Oral.
Graphic Photograms Graphic Photograms are a “camera-less” image making technique. They are created with printed images such as magazine cut- outs, newsprint.
Implement -Single Image Haze Removal Using Dark Channel Prior 張瀚元.
Che-An Wu Background substitution. Background Substitution AlphaMa p Trimap Depth Map Extract the foreground object and put into another background Objective.
Visual Information Processing. Human Perception V.S. Machine Perception  Human perception: pictorial information improvement for human interpretation.
Discuss the use of brain imaging technologies in investigating the relationship between biological factors and behaviour. (22) Discuss (22) – A considered.
Phil Morley Haze Removal.
렌즈왜곡 관련 논문 - 기반 논문: R.Y. Tsai, An Efficient and Accurate Camera Calibration Technique for 3D Machine Vision. Proceedings of IEEE Conference on Computer.
A Level Photography (Edexcel)
CASTLEFORD CAMERA CLUB
Gradient Domain High Dynamic Range Compression
CPSC 6040 Computer Graphics Images
Jun Shimamura, Naokazu Yokoya, Haruo Takemura and Kazumasa Yamazawa
Efficient Image Classification on Vertically Decomposed Data
EXPOSURE Reed's Cameras- Digital Photo 101.
A quick introduction to shooting digital images in RAW
Digital Image Formats: An Explanation
© 2005 University of Wisconsin
Fast Bilateral Filtering for the Display of High-Dynamic-Range Images
Efficient Image Classification on Vertically Decomposed Data
Knowledge-Based Organ Identification from CT Images
Single Image Haze Removal Using Dark Channel Prior
Rob Fergus Computer Vision
Shadow Detection and Removal
Gradient Domain High Dynamic Range Compression
University of Central Florida
Chapter Six Objectives
Announcements Project 1 is out today help session at the end of class.
Pixels, screens & printing
Presentation transcript:

Correcting Over-Exposure in Photographs Dong Guo, Yuan Cheng, Shaojie Zhuo, Terence Sim. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), San Francisco, 2010

Correcting Over-Exposure in Photographs Problems with overexposed areas Pixels receiving “too much” irradiance record almost white colors Color information is distorted (desaturated) Information is lost

Correcting Over-Exposure in Photographs Main Contribution Works with one single image Does not require user interaction

Correcting Over-Exposure in Photographs General Workflow Create a map of overexposed pixels Compress the dynamic-range in well-exposed areas Recover the lightness Correct the color

Correcting Over-Exposure in Photographs General Workflow Create a map of overexposed pixels

Correcting Over-Exposure in Photographs General Workflow 2. Compress the dynamic-range in well-exposed areas Analogue to Fattal’s method (2002) One among many other Tone Mapping methods

Correcting Over-Exposure in Photographs General Workflow 3. Recover the lightness E1: Compress the dynamic range (Fattal’s method) E2: Retain luminance in overexposed areas Constraint: keep very low light areas unchanged.

Correcting Over-Exposure in Photographs General Workflow 4. Correct the color \Psi: Color confidence = 1 - M First term: extract color from neighbors in overexposed areas (=> propagation from good pixels) Second term: keep the same color in well exposed areas

Correcting Over-Exposure in Photographs Results

Correcting Over-Exposure in Photographs Interesting references:

Correcting Over-Exposure in Photographs Interesting references: ANAT LEVIN’s work: http://www.wisdom.weizmann.ac.il/~levina/ A. Levin D. Lischinski and Y. Weiss. A Closed Form Solution to Natural Image Matting. IEEE Trans. Pattern Analysis and Machine Intelligence, Feb 2008 Powerful technique already used for: Alpha Matting, White Balance, Ghost Removal, Tone Mapping, Haze Removal Not directly cited in the paper

Correcting Over-Exposure in Photographs Interesting references: High Dynamic Range Imaging: Acquisition, Display, and Image-Based Lighting (The Morgan Kaufmann Series in Computer Graphics) Not directly cited in the paper