Scene Completion Using Millions of Photographs

What can you do with a million images? In this paper we present a new image completion algorithm powered by a huge database of photographs gathered from the Web. The algorithm patches up holes in images by finding similar image regions in the database that are not only seamless but also semantically valid. Our chief insight is that while the space of images is effectively infinite, the space of semantically differentiable scenes is actually not that large. For many image completion tasks we are able to find similar scenes which contain image fragments that will convincingly complete the image. Our algorithm is entirely data-driven, requiring no annotations or labelling by the user. Unlike existing image completion methods, our algorithm can generate a diverse set of results for each input image and we allow users to select among them. We demonstrate the superiority of our algorithm over existing image completion approaches

• Publication year

  2007

• Venue

  ACM Transactions on Graphics

• Publication date

  2007-07-29

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1145/3596711.3596783
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• LabelMe: A Database and Web-Based Tool for Image Annotation

  2008cited by this paper
• Scene completion using millions of photographs

  2008cited by this paper
• Tiny images

  2007cited by this paper
• Semantic Photo Synthesis

  2006cited by this paper
• Drag-and-drop pasting

  2006cited by this paper
• Photo tourism: exploring photo collections in 3D

  2006cited by this paper
• Image Completion Using Global Optimization

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

  2006cited by this paper
• What Is the Range of Surface Reconstructions from a Gradient Field?

  2006cited by this paper
• Image completion with structure propagation

  2005cited by this paper
• Hole Filling Through Photomontage

  2005cited by this paper
• Texture optimization for example-based synthesis

  2005cited by this paper
• Interactive Digital Photomontage

  2004cited by this paper
• Content Based Image Synthesis

  2004cited by this paper
• Poisson image editing

  2003cited by this paper
• Graphcut textures: image and video synthesis using graph cuts

  2003cited by this paper
• Fragment-based image completion

  2003cited by this paper
• Context-based vision system for place and object recognition

  2003cited by this paper
• Object removal by exemplar-based inpainting

  2003cited by this paper
• Image quilting for texture synthesis and transfer

  2001cited by this paper
• Fast approximate energy minimization via graph cuts

  2001cited by this paper
• Texture synthesis by non-parametric sampling

  1999cited by this paper
• Mosaic based representations of video sequences and their applications

  1995cited by this paper
• Laws of organization in perceptual forms.

  1938cited by this paper
• Transactions on Pattern Analysis and Machine Intelligence 1 Space-time Video Completion Draft Transactions on Pattern Analysis and Machine Intelligence 2

  year unknowncited by this paper

• Reliable and Fast Humans Removed Visual Scene Representation

  2026cites this paper
• Aligned Stable Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency

  2026cites this paper
• MDT-FI: Mask-Guided Dual-Branch Transformer With Texture and Structure Feature Interaction for Image Inpainting

  2026cites this paper
• Diff-GDAformer: A diffusion-guided dynamic attention transformer for image inpainting

  2026cites this paper
• FuPaSCo: Long-range and local context fusion for 3D panoptic scene completion

  2025cites this paper
• Large-Mask Inpainting for Airport Remote Sensing Images via Semantic Fine-Tuning

  2025cites this paper
• The Impact of AI on Transforming Concepts in Contemporary Photography

  2025cites this paper
• BlurPaint: Image Inpainting using Blurring Diffusion Models

  2025cites this paper
• Double salted HMAC signature with blockchain for faster and secure video integrity verification

  2025cites this paper
• An Integration Framework for the Inpainting and Colorization of Arbitrary Masked Grayscale Images

  2025cites this paper
• Complete Recovery and Health Status Detection of Roller Tank Lugs Using Image Inpainting Based on Unordered Image Stitching

  2025cites this paper
• PreciseCam: Precise Camera Control for Text-to-Image Generation

  2025cites this paper
• Visual-Neural-Inspired Image Inpainting for Specific Objects-of-Interest Imaging

  2025cites this paper
• MILD: Multi-Layer Diffusion Strategy for Complex and Precise Multi-IP Aware Human Erasing

  2025cites this paper
• Defurnishing with X-Ray Vision: Joint Removal of Furniture from Panoramas and Mesh

  2025cites this paper
• Large-Scale Completion of Ionospheric TEC Maps Using Machine Learning Models With Constraints Conditions

  2025cites this paper
• Image Restoration Based on Semantic Prior Aware Hierarchical Network and Multi-Scale Fusion Generator

  2025cites this paper
• PRISE: Privacy-pReserving Image Searchable Encryption Scheme for Intelligent Vehicle Systems

  2025cites this paper
• Exploring text-to-image generation models: Applications and cloud resource utilization

  2025cites this paper
• Efficient Hierarchical Feature Collaboration Transformer for Image Inpainting

  2025cites this paper
• ISRnet: Compressed Image Inpainting Based on Generative Adversarial Network

  2025cites this paper
• Image Completion Network Considering Global and Local Information

  2025cites this paper
• Global Ionospheric VTEC Data Completion Method Based on Aggregated Contextual-Transformation Generative Adversarial Nets

  2025cites this paper
• LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal

  2025cites this paper
• PARA UMA SOCIOLOGIA DA COMUNICAÇÃO ARTIFICIAL: CONDIÇÕES, TIPOS E IMPACTOS NA SOCIEDADE

  2025cites this paper
• Based on structure and texture dual-stream network for ancient mural restoration

  2025cites this paper
• Classical vs. Machine Learning-Based Inpainting for Enhanced Classification of Remote Sensing Image

  2025cites this paper
• 全局语义感知与纹理频域约束的激光干扰图像修复

  2025cites this paper
• SPC to 3D: Novel View Synthesis from Binary SPC via I2I translation

  2025cites this paper
• High-resolution image inpainting using a probabilistic framework for diverse images with large arbitrary masks

  2025cites this paper
• Agentic AI Workflow for End-to-End Prompt-Based Contextual Virtual Staging

  2025cites this paper
• Analyzing Face Image Inpainting with Attribute-Driven Generative Network

  2025cites this paper
• MILD: Multi-Layer Diffusion Strategy for Complex and Precise Multi-IP Aware Human Erasing

  2025cites this paper
• Mask Inpaints Using Downsampled Fast Fourier Convolution

  2024cites this paper
• AutoFill: An Automatic Approach to Filling Panoramic Images

  2024cites this paper
• BlipFill: Completing Authentic Images with BLIP-enhanced Subject Representation

  2024cites this paper
• MFI3D: masked face identification with 3D face reconstruction and deep learning

  2024cites this paper
• UniVision: A Unified Framework for Vision-Centric 3D Perception

  2024cites this paper
• ART IN PARTNERSHIP WITH HUMAN AND ARTIFICIAL INTELLIGENCE: CREATIVITY AND ALGORITHM

  2024cites this paper
• Automatic Face Image Restoration Based on an Improved Generative Adversarial Network

  2024cites this paper
• Quaternion Generative Adversarial Neural Networks and Applications to Color Image Inpainting

  2024cites this paper
• Local and global mixture network for image inpainting

  2024cites this paper
• Image inpainting algorithm based on inference attention module and two-stage network

  2024cites this paper
• High-Fidelity and Efficient Pluralistic Image Completion With Transformers

  2024cites this paper
• Diffusion Models for Cross-Domain Image-to-Image Translation with Paired and Partially Paired Datasets

  2024cites this paper
• Locally Conditioned GANs: Self-Supervised Local Patch Representation Learning for Conditional Generation

  2024cites this paper
• MapEx: Indoor Structure Exploration with Probabilistic Information Gain from Global Map Predictions

  2024cites this paper
• Model-Guided Generative Adversarial Networks for Unsupervised Fine-Grained Image Generation

  2024cites this paper
• Eyes Attribute Editing Assisted by Dual-Coordinate System and Multi-Probability Fusion Prediction

  2024cites this paper
• Image inpainting for corrupted images by using the semi-super resolution GAN

  2024cites this paper
• GroupDiff: Diffusion-based Group Portrait Editing

  2024cites this paper
• Towards Online Real-Time Memory-based Video Inpainting Transformers

  2024cites this paper
• Image inpainting method based on AU-GAN

  2024cites this paper
• An Empty Room is All We Want: Automatic Defurnishing of Indoor Panoramas

  2024cites this paper
• Art Image Inpainting With Style-Guided Dual-Branch Inpainting Network

  2024cites this paper
• Windowed-FourierMixer: Enhancing Clutter-Free Room Modeling with Fourier Transform

  2024cites this paper
• GAN-Based Two Stage Network for De-occlusion Face Image

  2024cites this paper
• Mutual encoder-decoder with bi-gated convolution for image inpainting

  2024cites this paper
• Edwards curve digital signature algorithm for video integrity verification on blockchain framework.

  2024cites this paper
• An Ancient Text Image Inpainting Algorithm via Edge Guide and Laplacian Pyramid Decomposition

  2024cites this paper
• ITrans: generative image inpainting with transformers

  2024cites this paper
• Bridging Global Context Interactions for High-Fidelity Pluralistic Image Completion

  2024cites this paper
• Anything in Any Scene: Photorealistic Video Object Insertion

  2024cites this paper
• Application Research on Image Recovery Technology Based on GAN

  2024cites this paper
• Unsupervised Representation Learning using Wasserstein Generative Adversarial Network

  2024cites this paper
• RealFill: Reference-Driven Generation for Authentic Image Completion

  2023cites this paper
• Multi-condition guided depth map completion method based on diffusion model

  2023cites this paper
• Progressive-Augmented-Based DeepFill for High-Resolution Image Inpainting

  2023cites this paper
• Joint face completion and super-resolution using multi-scale feature relation learning

  2023cites this paper
• Reconstruction of Partially Broken Vascular Structures in X-Ray Images via Vesselness-Loss-Based Multi-Scale Generative Adversarial Networks

  2023cites this paper
• Robust Image Inpainting Forensics by Using an Attention-Based Feature Pyramid Network

  2023cites this paper
• Seeing Behind Dynamic Occlusions with Event Cameras

  2023cites this paper
• A Review of Image Inpainting Methods Based on Deep Learning

  2023cites this paper
• MagConv: Mask-Guided Convolution for Image Inpainting

  2023cites this paper
• Photo Pre-Training, But for Sketch

  2023cites this paper
• Dr.Bokeh: DiffeRentiable Occlusion-Aware Bokeh Rendering

  2023cites this paper
• Toward Interactive Image Inpainting via Robust Sketch Refinement

  2023cites this paper
• LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model

  2023cites this paper
• A review of advances in image inpainting research

  2023cites this paper
• Multi-Temporal SamplePair Generation for Building Change Detection Promotion in Optical Remote Sensing Domain Based on Generative Adversarial Network

  2023cites this paper
• Advent of GAN: How does a generative AI create a moodboard?

  2023cites this paper
• Multi-stage Progressive Reasoning for Dunhuang Murals Inpainting

  2023cites this paper
• Paste, Inpaint and Harmonize via Denoising: Subject-Driven Image Editing with Pre-Trained Diffusion Model

  2023cites this paper
• RePGAN: image inpainting via residual partial connection and mask discriminator

  2023cites this paper
• Reference-guided Controllable Inpainting of Neural Radiance Fields

  2023cites this paper
• FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits

  2023cites this paper
• Towards Stable and Faithful Inpainting

  2023cites this paper
• A Unified Prompt-Guided In-Context Inpainting Framework for Reference-based Image Manipulations

  2023cites this paper
• Enhanced Inpainting Model Revitalizes Historical Paintings with Vision Transformer

  2023cites this paper
• Putting People in Their Place: Affordance-Aware Human Insertion into Scenes

  2023cites this paper
• Reference-Guided Large-Scale Face Inpainting With Identity and Texture Control

  2023cites this paper
• Persistent Nature: A Generative Model of Unbounded 3D Worlds

  2023cites this paper
• Performance analysis of generating cartoon like images from realistic images using various cycle GAN techniques

  2023cites this paper
• Look Ma, No Hands! Agent-Environment Factorization of Egocentric Videos

  2023cites this paper
• Texture Inpainting for Photogrammetric Models

  2023cites this paper
• Adapting to Skew: Imputing Spatiotemporal Urban Data with 3D Partial Convolutions and Biased Masking

  2023cites this paper
• EXIF as Language: Learning Cross-Modal Associations between Images and Camera Metadata

  2023influential citation
• RNON: image inpainting via repair network and optimization network

  2023cites this paper
• 3D-aware Blending with Generative NeRFs

  2023cites this paper
• Cross-Checking-Based Trademark Image Retrieval for Hot Company Detection

  2023cites this paper