Finding distractors in images

We propose a new computer vision task we call “distractor prediction.” Distractors are the regions of an image that draw attention away from the main subjects and reduce the overall image quality. Removing distractors-for example, using in-painting - can improve the composition of an image. In this work we created two datasets of images with user annotations to identify the characteristics of distractors. We use these datasets to train an algorithm to predict distractor maps. Finally, we use our predictor to automatically enhance images.

• Publication year

  2015

• Venue

  Computer Vision and Pattern Recognition

• Publication date

  2015-06-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/CVPR.2015.7298779
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Edge Boxes: Locating Object Proposals from Edges

  2014cited by this paper
• A Closer Look at Context: From Coxels to the Contextual Emergence of Object Saliency

  2014cited by this paper
• Multiscale Combinatorial Grouping

  2014cited by this paper
• What Makes a Patch Distinct?

  2013influential reference
• Restoring an Image Taken through a Window Covered with Dirt or Rain

  2013cited by this paper
• Learning the Change for Automatic Image Cropping

  2013cited by this paper
• Real-time scene text localization and recognition

  2012cited by this paper
• AVA: A large-scale database for aesthetic visual analysis

  2012cited by this paper
• Fusing generic objectness and visual saliency for salient object detection

  2011cited by this paper
• Content-based photo quality assessment

  2011cited by this paper
• Global contrast based salient region detection

  2011cited by this paper
• A comparative study of image retargeting

  2010cited by this paper
• Studying the effect of optimizing the image quality in saliency regions at the expense of background content

  2010cited by this paper
• Object Detection with Discriminatively Trained Part Based Models

  2010cited by this paper
• A framework for visual saliency detection with applications to image thumbnailing

  2009cited by this paper
• Recognizing linked events: Searching the space of feasible explanations

  2009cited by this paper
• PatchMatch: a randomized correspondence algorithm for structural image editing

  2009cited by this paper
• Learning to predict where humans look

  2009cited by this paper
• Studying the added value of visual attention in objective image quality metrics based on eye movement data

  2009cited by this paper
• Example-Based Cosmetic Transfer

  2007cited by this paper
• Saliency Detection: A Spectral Residual Approach

  2007cited by this paper
• Seam Carving for Content-Aware Image Resizing

  2007cited by this paper
• Geometric Computing in Shape Space

  2007cited by this paper
• The Design of High-Level Features for Photo Quality Assessment

  2006cited by this paper
• Graph-Based Visual Saliency

  2006cited by this paper
• Working Set Selection Using Second Order Information for Training Support Vector Machines

  2005cited by this paper
• De-emphasis of distracting image regions using texture power maps

  2005cited by this paper
• On missing data treatment for degraded video and film archives: a survey and a new Bayesian approach

  2004cited by this paper
• Automatic thumbnail cropping and its effectiveness

  2003cited by this paper
• Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

  2001cited by this paper
• Robust Real-Time Face Detection

  2001cited by this paper
• Robust Real-time Object Detection

  2001cited by this paper
• A saliency-based search mechanism for overt and covert shifts of visual attention.

  2000cited by this paper
• Detection and removal of line scratches in motion picture films

  1999cited by this paper
• Bagging Predictors

  1996cited by this paper
• Regression Shrinkage and Selection via the Lasso

  1996influential reference
• Presented at: 2nd Annual IEEE International Conference on Image

  1995cited by this paper

• Comparing Perspective in Drawings, Photographs, and Perception

  2025cites this paper
• Improving Threat Object Recognition for X-Ray Baggage Screening Using Distraction Removal Techniques

  2023cites this paper
• SimpSON: Simplifying Photo Cleanup with Single-Click Distracting Object Segmentation Network

  2023cites this paper
• DeclutterCam: A Photographic Assistant System with Clutter Detection and Removal

  2022cites this paper
• Predicting Visual Attention and Distraction During Visual Search Using Convolutional Neural Networks

  2022cites this paper
• Dynamic Guidance for Decluttering Photographic Compositions

  2021influential citation
• Designing Photography Guidance for Rapid In-Camera Iteration

  2021cites this paper
• Dynamic Guidance for Declutering Photographic Compositions

  2021cites this paper
• Benign Object Detection and Distractor Removal in 2D Baggage Scans

  2021influential citation
• Saliency-Guided Image Translation

  2021cites this paper
• Deep Saliency Prior for Reducing Visual Distraction

  2021cites this paper
• Photobomb Defusal Expert: Automatically Remove Distracting People From Photos

  2020cites this paper
• Saliency-based image correction for colorblind patients

  2020cites this paper
• Look here! A parametric learning based approach to redirect visual attention

  2020cites this paper
• Smart image enhancement technique by removal of undesirable objects/background from the image

  2020influential citation
• Saliency-aware inter-image color transfer for image manipulation

  2019cites this paper
• Blind Visual Motif Removal From a Single Image

  2019cites this paper
• Extracting Regular FOV Shots from 360 Event Footage

  2018cites this paper
• Detecting and Removing Visual Distractors for Video Aesthetic Enhancement

  2018influential citation
• Automatic Stranger Remover in Photo by Deep Learning Segmentation

  2018cites this paper
• Training Deep Networks to be Spatially Sensitive

  2017influential citation
• Photo Manipulation, The Easy Way

  2017cites this paper
• Visual distractors detecting in images using TPTSSR

  2017influential citation
• cvpaper.challenge in 2016: Futuristic Computer Vision through 1, 600 Papers Survey

  2017cites this paper
• cvpaper.challenge in 2015 - A review of CVPR2015 and DeepSurvey

  2016cites this paper
• Saliency driven image manipulation

  2016influential citation
• cvpaper.challenge in CVPR2015 -- A review of CVPR2015

  2015cites this paper
• List of references

  2015cites this paper