Estimating perception of scene layout properties from global image features.

The relationship between image features and scene structure is central to the study of human visual perception and computer vision, but many of the specifics of real-world layout perception remain unknown. We do not know which image features are relevant to perceiving layout properties, or whether those features provide the same information for every type of image. Furthermore, we do not know the spatial resolutions required for perceiving different properties. This paper describes an experiment and a computational model that provides new insights on these issues. Humans perceive the global spatial layout properties such as dominant depth, openness, and perspective, from a single image. This work describes an algorithm that reliably predicts human layout judgments. This model's predictions are general, not specific to the observers it trained on. Analysis reveals that the optimal spatial resolutions for determining layout vary with the content of the space and the property being estimated. Openness is best estimated at high resolution, depth is best estimated at medium resolution, and perspective is best estimated at low resolution. Given the reliability and simplicity of estimating the global layout of real-world environments, this model could help resolve perceptual ambiguities encountered by more detailed scene reconstruction schemas.

• Publication year

  2011

• Venue

  Journal of Vision

• Publication date

  2011-01-06

• Fields of study

  Medicine, Computer Science

• Identifiers
  DOI 10.1167/10.1.2PMID 20143895
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Journal of Experimental Psychology : Human Perception and Performance High-Level Aftereffects to Global Scene Properties

  2010cited by this paper
• Natural-Scene Statistics Predict How the Figure–Ground Cue of Convexity Affects Human Depth Perception

  2010cited by this paper
• Perceived size is affected by blur and accommodation

  2010cited by this paper
• Blur and accommodation are metric depth cues

  2010cited by this paper
• Prior expectations in slant perception: Has the visual system internalized natural scene geometry?

  2010cited by this paper
• Recognition of natural scenes from global properties: seeing the forest without representing the trees.

  2009influential reference
• Priming of simple and complex scene layout: rapid function from the intermediate level.

  2009cited by this paper
• How many pixels make an image?

  2009influential reference
• Make3D: Learning 3D Scene Structure from a Single Still Image

  2009cited by this paper
• The Briefest of Glances: The Time Course of Natural Scene Understanding

  2009influential reference
• Inferring spatial layout from a single image via depth-ordered grouping

  2008cited by this paper
• Can similar scenes help surface layout estimation?

  2008cited by this paper
• Parahippocampal and retrosplenial contributions to human spatial navigation.

  2008cited by this paper
• Recovering Surface Layout from an Image

  2007cited by this paper
• Semantic Modeling of Natural Scenes for Content-Based Image Retrieval

  2007cited by this paper
• Processing scene context: fast categorization and object interference.

  2007cited by this paper
• Losing sight of the bigger picture: peripheral field loss compresses representations of space.

  2007cited by this paper
• Shape From Shading

  2006cited by this paper
• Individual skill differences and large-scale environmental learning.

  2006cited by this paper
• Building the gist of a scene: the role of global image features in recognition.

  2006cited by this paper
• Environmental context influences visually perceived distance

  2006cited by this paper
• Contextual guidance of eye movements and attention in real-world scenes: the role of global features in object search.

  2006cited by this paper
• The representation of perceived angular size in human primary visual cortex

  2006cited by this paper
• Pattern Recognition and Machine Learning

  2006cited by this paper
• Why pictures look right when viewed from the wrong place

  2005cited by this paper
• Where should you sit to watch a movie?

  2005cited by this paper
• A Bayesian hierarchical model for learning natural scene categories

  2005cited by this paper
• The use of visual information in natural scenes

  2005cited by this paper
• Natural-scene geometry predicts the perception of angles and line orientation.

  2005cited by this paper
• Focus cues affect perceived depth.

  2005cited by this paper
• Ordinal configural cues combine with metric disparity in depth perception.

  2005cited by this paper
• Why Is Spatial Stereoresolution So Low?

  2004cited by this paper
• Perceiving distance accurately by a directional process of integrating ground information

  2004cited by this paper
• Perceiving virtual geographical slant: action influences perception.

  2004cited by this paper
• Behavioral and Neuroimaging Evidence for a Contribution of Color and Texture Information to Scene Classification in a Patient with Visual Form Agnosia

  2004cited by this paper
• When is scene identification just texture recognition?

  2004cited by this paper
• Representation and perception of spatial layout

  2003cited by this paper
• Image/source statistics of surfaces in natural scenes

  2003cited by this paper
• Representation and perception of scenic layout.

  2003cited by this paper
• Stereoscopic depth processing in the visual cortex: a coarse-to-fine mechanism

  2003cited by this paper
• Depth Estimation from Image Structure

  2002influential reference
• Scene-Centered Description from Spatial Envelope Properties

  2002influential reference
• Biologically Motivated Computer Vision

  2002cited by this paper
• Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

  2001influential reference
• Bubbles: a technique to reveal the use of information in recognition tasks.

  2001cited by this paper
• A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients

  2000cited by this paper
• Vision

  2000cited by this paper
• Single View Metrology

  2000cited by this paper
• When Far Becomes Near: Remapping of Space by Tool Use

  2000cited by this paper
• Similarity and Features of Natural Textures

  1999cited by this paper
• Manhattan World: compass direction from a single image by Bayesian inference

  1999cited by this paper
• Dr. Angry and Mr. Smile: when categorization flexibly modifies the perception of faces in rapid visual presentations.

  1999cited by this paper
• On image classification: city images vs. landscapes

  1998cited by this paper
• Perceptual image similarity experiments

  1998cited by this paper
• Mental representations of large and small spatial layouts are orientation dependent.

  1998cited by this paper
• The nature of mathematical modeling

  1998cited by this paper
• The Correlational Structure of Natural Images and the Calibration of Spatial Representations

  1997cited by this paper
• Coarse blobs or fine edges? Evidence that information diagnosticity changes the perception of complex visual stimuli.

  1997cited by this paper
• Priming Spatial Layout of Scenes

  1997cited by this paper
• Perceptual categories for spatial layout.

  1997cited by this paper
• Planar surface orientation from texture spatial frequencies

  1995cited by this paper
• Perceiving geographical slant

  1995cited by this paper
• Pyramid-based texture analysis/synthesis

  1995cited by this paper
• From Blobs to Boundary Edges: Evidence for Time- and Spatial-Scale-Dependent Scene Recognition

  1994cited by this paper
• Research Design and Statistical Analysis

  1991cited by this paper
• A stereoscopic view of visual processing streams.

  1990cited by this paper
• Relations between the statistics of natural images and the response properties of cortical cells.

  1987cited by this paper
• Determining vanishing points from perspective images

  1984cited by this paper
• Fractal-Based Description of Natural Scenes

  1984cited by this paper
• Fractal-Based Description

  1983cited by this paper
• Interpreting Line Drawings as Three-Dimensional Surfaces

  1980cited by this paper
• The Ecological Approach to Visual Perception

  1979cited by this paper
• Depth from spatial frequency difference: an old kind of stereopsis?

  1979cited by this paper
• Please Scroll down for Article Visual Cognition Modelling Search for People in 900 Scenes: a Combined Source Model of Eye Guidance

  year unknowncited by this paper

• Maintaining visual stability in naturalistic scenes: The roles of trans-saccadic memory and default assumptions.

  2025cites this paper
• A 2D Gabor-wavelet baseline model out-performs a 3D surface model in scene-responsive cortex

  2025cites this paper
• Post-Saccadic Disruption of Semantic Category Information in Naturalistic Scenes

  2025cites this paper
• Auditory discrimination and identification of time of day for natural soundscapes

  2025cites this paper
• The impact of scene inversion on early scene-selective activity.

  2025cites this paper
• Preliminary Evidence for Global Properties in Human Listeners During Natural Auditory Scene Perception

  2024influential citation
• Mean orientation discrimination based on proximal stimuli

  2024cites this paper
• Memorability-based multimedia analytics for robotic interestingness prediction system using trimmed Q-learning algorithm

  2023cites this paper
• Characterising and dissecting human perception of scene complexity.

  2022cites this paper
• Contour-guided saliency detection with long-range interactions

  2022cites this paper
• Category systems for real-world scenes

  2021influential citation
• Prediction of Natural Image Saliency for Synthetic Images

  2021cites this paper
• Contour features predict valence and threat judgements in scenes

  2021cites this paper
• Feature-specificity in visual statistical summary processing

  2020cites this paper
• Artificially-generated scenes demonstrate the importance of global scene properties for scene perception.

  2020cites this paper
• Prior Expectations of Motion Direction Modulate Early Sensory Processing

  2020cites this paper
• Self-generation and sound intensity interactively modulate perceptual bias, but not perceptual sensitivity

  2020cites this paper
• Anticipatory reinstatement of expected perceptual events during visual sequence learning

  2020cites this paper
• A structure-guided approach to the prediction of natural image saliency

  2020cites this paper
• Visual statistical learning and integration of perceptual priors are intact in attention deficit hyperactivity disorder

  2020cites this paper
• Performance Monitoring for Sensorimotor Confidence: A Visuomotor Tracking Study

  2019cites this paper
• When expectations are not met: unraveling the computational mechanisms underlying the effect of expectation on perceptual thresholds

  2019cites this paper
• Bayesian transfer in a complex spatial localization task

  2019cites this paper
• Line Drawings of Natural Scenes Guide Visual Attention

  2019cites this paper
• Interaction between static visual cues and force-feedback on the perception of mass of virtual objects

  2018cites this paper
• A deep-learning based feature hybrid framework for spatiotemporal saliency detection inside videos

  2018cites this paper
• The influence of behavioral relevance on the processing of global scene properties: An ERP study

  2018cites this paper
• Establishing reference scales for scene naturalness and openness

  2018cites this paper
• Acquisition of visual priors and induced hallucinations in chronic schizophrenia

  2018cites this paper
• The First Moments of Medical Image Perception

  2018cites this paper
• Processing global properties in Scene Categorization

  2017cites this paper
• Prior expectations induce prestimulus sensory templates

  2017cites this paper
• Prior expectations induce pre-stimulus sensory templates

  2017cites this paper
• Learning features in a complex and changing environment: A distribution-based framework for visual attention and vision in general.

  2017cites this paper
• Bridging the semantic gap with human perception based features for scene categorization

  2017cites this paper
• Global Ensemble Texture Representations are Critical to Rapid Scene Perception

  2017cites this paper
• Autistic traits, but not schizotypy, predict increased weighting of sensory information in Bayesian visual integration

  2017cites this paper
• Saliency prediction with scene structural guidance

  2017cites this paper
• Neurocognitive investigation of object-in-scene representations

  2017cites this paper
• A New Framework for Measuring 2D and 3D Visual Information in Terms of Entropy

  2016cites this paper
• Assessing human depth perception for 2D and 3D stereoscopic images and video and its relation with the overall 3D QoE

  2016influential citation
• Generalization of prior information for rapid Bayesian time estimation

  2016cites this paper
• A general account of peripheral encoding also predicts scene perception performance.

  2016cites this paper
• Phase-Dependent Interactions in Visual Cortex to Combinations of First- and Second-Order Stimuli

  2016cites this paper
• Vanishing point attracts gaze in free-viewing and visual search tasks

  2015cites this paper
• Fall 9-2014 Learning Statistical Features of Scene Images

  2015influential citation
• Proto-object categorisation and local gist vision using low-level spatial features

  2015cites this paper
• Open perceptual binocular and monocular descriptors for stereoscopic 3D images and video characterization

  2015cites this paper
• Adaptation and adaptation transfer characteristics of five different saccade types in the monkey.

  2015cites this paper
• roto-object categorisation and local gist vision using low-level patial features aime

  2015cites this paper
• Multiple object properties drive scene-selective regions.

  2014cites this paper
• Monocular depth estimation in images and sequences using occlusion cues

  2014cites this paper
• Spatial and temporal visual attention prediction in videos using eye movement data

  2014cites this paper
• Parametric Coding of the Size and Clutter of Natural Scenes in the Human Brain.

  2014cites this paper
• Form-Cue Invariant Second-Order Neuronal Responses to Contrast Modulation in Primate Area V2

  2014cites this paper
• Learning Statistical Features of Scene Images

  2014influential citation
• Selectivity for large nonmanipulable objects in scene-selective visual cortex does not require visual experience

  2013cites this paper
• Single image ground plane estimation

  2013cites this paper
• Biologically inspired task oriented gist model for scene classification

  2013cites this paper
• Human-inspired features for natural scene classification

  2013cites this paper
• Visual Features for Scene Recognition and Reorientation

  2013cites this paper
• 51 Scene Perception

  2013cites this paper
• Visualizing Natural Image Statistics

  2013cites this paper
• CHAPITRE 21 – Physiologie

  2013cites this paper
• Learning global properties of scene images based on their correlational structures

  2012influential citation
• Natural scene classification, annotation and retrieval : developing different approaches for semantic scene modelling based on Bag of Visual Words

  2012cites this paper
• Perceptual depth indicator for S-3D content based on binocular and monocular cues

  2012influential citation
• Local object gist: meaningful shapes and spatial layout at a very early stage of visual processing

  2012cites this paper
• Towards a Descriptive Depth Index for 3D Content: Measuring Perspective Depth Cues

  2012influential citation
• Evaluating Depth Perception of 3D Stereoscopic Videos

  2012cites this paper
• Spatially Pooled Contrast Responses Predict Neural and Perceptual Similarity of Naturalistic Image Categories

  2012cites this paper
• A Cortical Framework for Scene Categorisation

  2011cites this paper
• Vision in 3D Environments: Representing, perceiving, and remembering the shape of visual space

  2011cites this paper
• Estimating scene typicality from human ratings and image features Citation

  2011cites this paper
• Prediction of the inter-observer visual congruency (IOVC) and application to image ranking

  2011cites this paper
• Real-World Scene Representations in High-Level Visual Cortex: It's the Spaces More Than the Places

  2011cites this paper
• Fusing integrated visual vocabularies-based bag of visual words and weighted colour moments on spatial pyramid layout for natural scene image classification

  2011cites this paper
• Estimating scene typicality from human ratings and image features

  2011cites this paper
• Predicting saliency using two contextual priors: The dominant depth and the horizon line

  2011cites this paper
• Scene image clustering based on boosting and GMM

  2011cites this paper
• Extrapolating spatial layout in scene representations

  2010cites this paper
• Getting real-sensory processing of natural stimuli.

  2010cites this paper
• Behavioral Studies of Scene Perception Historical Perspective

  year unknowncites this paper
• Source (or Part of the following Source): Type Article Title Spatially Pooled Contrast Responses Predict Neural and Perceptual Similarity of Naturalistic Image Categories Author(s) Spatially Pooled Contrast Responses Predict Neural and Perceptual Similarity of Naturalistic Image Categories

  year unknowncites this paper