Learning Representations for Automatic Colorization
Not on the map. Why?
Abstract (arXiv)
We develop a fully automatic image colorization system. Our approach leverages recent advances in deep networks, exploiting both low-level and semantic representations. As many scene elements naturally appear according to multimodal color distributions, we train our model to predict per-pixel color histograms. This intermediate output can be used to automatically generate a color image, or further manipulated prior to image formation. On both fully and partially automatic colorization tasks, we outperform existing methods. We also explore colorization as a vehicle for self-supervised visual representation learning.
Key facts. Cited by 251 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Mar 2016.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 80; 2022: 76; 2023: 50; 2024: 29; 2025: 12; 2026: 4.
251 papers.
Sort:
By area:
- 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
- 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
- 2023Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecturecited by 1,039
- 2022Denoising Diffusion Restoration Modelscited by 963
- 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
- 2024Revisiting Feature Prediction for Learning Visual Representations from Videocited by 531
- 2021GAN Inversion: A Surveycited by 367
- 2022Masked Siamese Networks for Label-Efficient Learningcited by 302
- 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
- 2023A Cookbook of Self-Supervised Learningcited by 250
- 2021Pre-training Molecular Graph Representation with 3D Geometrycited by 248
- 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
38 more
- 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 207
- 2021DetCo: Unsupervised Contrastive Learning for Object Detectioncited by 205
- 2023Generative Diffusion Prior for Unified Image Restoration and Enhancementcited by 199
- 2021SCARF: Self-Supervised Contrastive Learning using Random Feature Corruptioncited by 156
- 2021Efficient Self-supervised Vision Transformers for Representation Learningcited by 149
- 2021Self-Supervised Representation Learning: Introduction, Advances and Challengescited by 148
- 2022Self-supervised Learning in Remote Sensing: A Reviewcited by 137
- 2023The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimationcited by 116
- 2021SiT: Self-supervised vIsion Transformercited by 99
- 2021Colorization Transformercited by 89
- 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 88
- 2023Monocular Depth Estimation using Diffusion Modelscited by 87
- 2022Self-Supervised Learning for Videos: A Surveycited by 85
- 2021Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptationcited by 83
- 2022My View is the Best View: Procedure Learning from Egocentric Videoscited by 81
- 2021Robust Audio-Visual Instance Discriminationcited by 80
- 2022Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervisioncited by 80
- 2021Self-Supervised Learning with Kernel Dependence Maximizationcited by 77
- 2021Unsupervised Object-Level Representation Learning from Scene Imagescited by 72
- 2022Masked Frequency Modeling for Self-Supervised Visual Pre-Trainingcited by 71
- 2023Best of Both Worlds: Multimodal Contrastive Learning with Tabular and Imaging Datacited by 69
- 2022Unsupervised Object Localization: Observing the Background to Discover Objectscited by 66
- 2021Spatially Consistent Representation Learningcited by 64
- 2021Preservational Learning Improves Self-supervised Medical Image Models by Reconstructing Diverse Contextscited by 60
- 2022Bootstrapped Masked Autoencoders for Vision BERT Pretrainingcited by 60
- 2021Few-Shot Lifelong Learningcited by 59
- 2023GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restorationcited by 59
- 2022A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyondcited by 58
- 2021Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learningcited by 56
- 2021Towards Vivid and Diverse Image Colorization with Generative Color Priorcited by 55
- 2022Robust Cross-Modal Representation Learning with Progressive Self-Distillationcited by 55
- 2021Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuningcited by 50
- 2021Unsupervised Action Segmentation by Joint Representation Learning and Online Clusteringcited by 49
- 2021Improving Transferability of Representations via Augmentation-Aware Self-Supervisioncited by 49
- 2021Self-Supervised Material and Texture Representation Learning for Remote Sensing Taskscited by 49
- 2021Learning by Aligning Videos in Timecited by 48
- 2021Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learningcited by 47
- 2022HCSC: Hierarchical Contrastive Selective Codingcited by 43
50 most cited of 251 All 251 (JSON)
- 2026A Human-in-the-Loop Deep Learning Framework for Color Reconstruction of Lenticular Films3 Aug 2026
- 2026Beyond Model Size: Probing the Gaps in Visual in-Context Learning by Training a Tiny Model9 Jun 2026
- 2026Information theoretic underpinning of self-supervised learning by clustering12 May 2026
- 2026Consistency Regularised Gradient Flows for Inverse Problems8 May 2026
- 2025Self-Supervised AI-Generated Image Detection: A Camera Metadata Perspective5 Dec 2025
- 2025Conditional Representation Learning for Customized Tasks6 Oct 2025
- 2025REMAP: Regularized Matching and Partial Alignment of Video Embeddings29 Sep 2025
- 2025Structure-preserving Feature Alignment for Old Photo Colorization18 Aug 2025
- 2025Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport21 Jul 2025
- 2025Paired and Unpaired Image to Image Translation using Generative Adversarial Networks22 May 2025
- 2025Self-Supervised Learning for Image Segmentation: A Comprehensive Survey19 May 2025
- 2025Enhancing User Sequence Modeling through Barlow Twins-based Self-Supervised Learning2 May 2025
38 more
- 2025Joint Self-Supervised Video Alignment and Action Segmentation21 Mar 2025
- 2025Utilization of Neighbor Information for Image Classification with Different Levels of Supervision18 Mar 2025
- 2025Convolutional Deep Colorization for Image Compression: A Color Grid Based Approach8 Feb 2025
- 2025Self-supervised Benchmark Lottery on ImageNet: Do Marginal Improvements Translate to Improvements on Similar Datasets?26 Jan 2025
- 2024Enabling Region-Specific Control via Lassos in Point-Based Colorization18 Dec 2024
- 2024KDC-MAE: Knowledge Distilled Contrastive Mask Auto-Encoder19 Nov 2024
- 2024Understanding the Role of Equivariance in Self-supervised Learning10 Nov 2024
- 2024Calibrated Cache Model for Few-Shot Vision-Language Model Adaptation11 Oct 2024
- 2024Computer-aided Colorization State-of-the-science: A Survey3 Oct 2024
- 2024UniEmoX: Cross-modal Semantic-Guided Large-Scale Pretraining for Universal Scene Emotion Perception27 Sep 2024
- 2024Patch-Based Contrastive Learning and Memory Consolidation for Online Unsupervised Continual Learning24 Sep 2024
- 2024Bridging the Domain Gap for Flight-Ready Spaceborne Vision18 Sep 2024
- 2024Leveraging Superfluous Information in Contrastive Representation Learning19 Aug 2024
- 2024AggSS: An Aggregated Self-Supervised Approach for Class-Incremental Learning8 Aug 2024
- 2024Diffusion Model Meets Non-Exemplar Class-Incremental Learning and Beyond6 Aug 2024
- 2024Self-Supervised Learning for Text Recognition: A Critical Survey29 Jul 2024
- 2024Universal Facial Encoding of Codec Avatars from VR Headsets17 Jul 2024
- 2024Progressive Proxy Anchor Propagation for Unsupervised Semantic Segmentation17 Jul 2024
- 2024Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked Pretraining1 Jul 2024
- 2024The Brain's Bitter Lesson: Scaling Speech Decoding With Self-Supervised Learning6 Jun 2024
- 2024In-Context Symmetries: Self-Supervised Learning through Contextual World Models28 May 2024
- 2024DINO as a von Mises-Fisher mixture model17 May 2024
- 2024ColorMNet: A Memory-based Deep Spatial-Temporal Feature Propagation Network for Video Colorization9 Apr 2024
- 2024Automatic Controllable Colorization via Imagination8 Apr 2024
- 2024GenN2N: Generative NeRF2NeRF Translation3 Apr 2024
- 2024Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning27 Mar 2024
- 2024HyperColorization: Propagating spatially sparse noisy spectral clues for reconstructing hyperspectral images18 Mar 2024
- 2024CCC++: Optimized Color Classified Colorization with Segment Anything Model (SAM) Empowered Object Selective Color Harmonization18 Mar 2024
- 2024CCC: Color Classified Colorization3 Mar 2024
- 2024Colorizing Monochromatic Radiance Fields19 Feb 2024
- 2024Control Color: Multimodal Diffusion-based Interactive Image Colorization16 Feb 2024
- 2024Revisiting Feature Prediction for Learning Visual Representations from Video15 Feb 2024
- 2024MetaISP -- Exploiting Global Scene Structure for Accurate Multi-Device Color Rendition6 Jan 2024
- 2023Bootstrap Masked Visual Modeling via Hard Patches Mining21 Dec 2023
- 2023SPDGAN: A Generative Adversarial Network based on SPD Manifold Learning for Automatic Image Colorization21 Dec 2023
- 2023Set Features for Anomaly Detection24 Nov 2023
- 2023Pre-Training LiDAR-Based 3D Object Detectors Through Colorization23 Oct 2023
- 2023DARTH: Holistic Test-time Adaptation for Multiple Object Tracking3 Oct 2023
50 newest of 251 All 251 (JSON)
- 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
- 2022Denoising Diffusion Restoration Modelscited by 963
- 2023Generative Diffusion Prior for Unified Image Restoration and Enhancementcited by 199
- 2023The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimationcited by 116
- 2023Monocular Depth Estimation using Diffusion Modelscited by 87
- 2023GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restorationcited by 59
- 2023A Residual Diffusion Model for High Perceptual Quality Codec Augmentationcited by 35
- 2023ViCo: Plug-and-play Visual Condition for Personalized Text-to-image Generationcited by 23
- 2023Accelerating Diffusion Models for Inverse Problems through Shortcut Samplingcited by 21
- 2023Improved Diffusion-based Image Colorization via Piggybacked Modelscited by 15
- 2023Video Colorization with Pre-trained Text-to-Image Diffusion Modelscited by 11
- 2023L-CAD: Language-based Colorization with Any-level Descriptions using Diffusion Priorscited by 5
12 most cited of 15 All 15 (JSON)
- 2026Consistency Regularised Gradient Flows for Inverse Problems8 May 2026
- 2024Diffusion Model Meets Non-Exemplar Class-Incremental Learning and Beyond6 Aug 2024
- 2023DiffColor: Toward High Fidelity Text-Guided Image Colorization with Diffusion Models3 Aug 2023
- 2023The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation2 Jun 2023
- 2023Video Colorization with Pre-trained Text-to-Image Diffusion Models2 Jun 2023
- 2023ViCo: Plug-and-play Visual Condition for Personalized Text-to-image Generation1 Jun 2023
- 2023Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling26 May 2023
- 2023L-CAD: Language-based Colorization with Any-level Descriptions using Diffusion Priors24 May 2023
- 2023Improved Diffusion-based Image Colorization via Piggybacked Models21 Apr 2023
- 2023Generative Diffusion Prior for Unified Image Restoration and Enhancement3 Apr 2023
- 2023Monocular Depth Estimation using Diffusion Models28 Feb 2023
- 2023GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration30 Jan 2023
12 newest of 15 All 15 (JSON)
- 2022Robust Cross-Modal Representation Learning with Progressive Self-Distillationcited by 55
- 2024DINO as a von Mises-Fisher mixture modelcited by 15
- 2024KDC-MAE: Knowledge Distilled Contrastive Mask Auto-Encodercited by 0
- 2024KDC-MAE: Knowledge Distilled Contrastive Mask Auto-Encoder19 Nov 2024
- 2024DINO as a von Mises-Fisher mixture model17 May 2024
- 2022Robust Cross-Modal Representation Learning with Progressive Self-Distillation10 Apr 2022
- 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
- 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
- 2021GAN Inversion: A Surveycited by 367
- 2022Masked Siamese Networks for Label-Efficient Learningcited by 302
- 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
- 2023A Cookbook of Self-Supervised Learningcited by 250
- 2021Pre-training Molecular Graph Representation with 3D Geometrycited by 248
- 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
- 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 207
- 2021DetCo: Unsupervised Contrastive Learning for Object Detectioncited by 205
- 2021SCARF: Self-Supervised Contrastive Learning using Random Feature Corruptioncited by 156
- 2021Efficient Self-supervised Vision Transformers for Representation Learningcited by 149
12 most cited of 229 All 229 (JSON)
- 2026A Human-in-the-Loop Deep Learning Framework for Color Reconstruction of Lenticular Films3 Aug 2026
- 2026Beyond Model Size: Probing the Gaps in Visual in-Context Learning by Training a Tiny Model9 Jun 2026
- 2026Information theoretic underpinning of self-supervised learning by clustering12 May 2026
- 2025Self-Supervised AI-Generated Image Detection: A Camera Metadata Perspective5 Dec 2025
- 2025Conditional Representation Learning for Customized Tasks6 Oct 2025
- 2025REMAP: Regularized Matching and Partial Alignment of Video Embeddings29 Sep 2025
- 2025Structure-preserving Feature Alignment for Old Photo Colorization18 Aug 2025
- 2025Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport21 Jul 2025
- 2025Paired and Unpaired Image to Image Translation using Generative Adversarial Networks22 May 2025
- 2025Self-Supervised Learning for Image Segmentation: A Comprehensive Survey19 May 2025
- 2025Enhancing User Sequence Modeling through Barlow Twins-based Self-Supervised Learning2 May 2025
- 2025Joint Self-Supervised Video Alignment and Action Segmentation21 Mar 2025
12 newest of 229 All 229 (JSON)