Artificial Intelligence for Geometry-Based Feature Extraction, Analysis and Synthesis in Artistic Images: A Survey
Not on the map. Why?
Abstract (arXiv)
Artificial Intelligence significantly enhances the visual art industry by analyzing, identifying and generating digitized artistic images. This review highlights the substantial benefits of integrating geometric data into AI models, addressing challenges such as high inter-class variations, domain gaps, and the separation of style from content by incorporating geometric information. Models not only improve AI-generated graphics synthesis quality, but also effectively distinguish between style and content, utilizing inherent model biases and shared data traits. We explore methods like geometric data extraction from artistic images, the impact on human perception, and its use in discriminative tasks. The review also discusses the potential for improving data quality through innovative annotation techniques and the use of geometric data to enhance model adaptability and output refinement. Overall, incorporating geometric guidance boosts model performance in classification and synthesis tasks, providing crucial insights for future AI applications in the visual arts domain.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 84 of its 192 references that are in the map. First posted on arXiv 2 Dec 2024.
Builds on
84 of 192 references.
References · 84
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
- 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
- 2017Deeper, Broader and Artier Domain Generalizationcited by 983
- 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 493
- 2023Training-Free Layout Control with Cross-Attention Guidancecited by 312
- 2021Learning Object-Compositional Neural Radiance Field for Editable Scene Renderingcited by 228
- 2020Deep Learning-Based Human Pose Estimation: A Surveycited by 205
- 2021Point-Based Neural Rendering with Per-View Optimizationcited by 188
- 2023Cut and Learn for Unsupervised Object Detection and Instance Segmentationcited by 186
- 2015Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Featurecited by 181
38 more
- 2019Style Transfer by Relaxed Optimal Transport and Self-Similaritycited by 167
- 2022StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learningcited by 140
- 2023Locally Attentional SDF Diffusion for Controllable 3D Shape Generationcited by 129
- 2023Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenescited by 68
- 2022Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidancecited by 67
- 2017Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regressioncited by 66
- 2020Artificial Intelligence in the Creative Industries: A Reviewcited by 61
- 2021Understanding and Creating Art with AI: Review and Outlookcited by 60
- 2023Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Modelscited by 59
- 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 59
- 2020Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondencecited by 53
- 2022UPST-NeRF: Universal Photorealistic Style Transfer of Neural Radiance Fields for 3D Scenecited by 47
- 2022SceneComposer: Any-Level Semantic Image Synthesiscited by 43
- 2022The Met Dataset: Instance-level Recognition for Artworkscited by 40
- 2023PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervisioncited by 36
- 2021Rethinking Supervised Pre-training for Better Downstream Transferringcited by 35
- 2016Learning Aligned Cross-Modal Representations from Weakly Aligned Datacited by 34
- 2018User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networkscited by 32
- 2020Deformable Style Transfercited by 31
- 2021Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generationcited by 30
- 2019Neural Painters: A learned differentiable constraint for generating brushstroke paintingscited by 28
- 2018Weakly Supervised Object Detection in Artworkscited by 27
- 2019Discovering Visual Patterns in Art Collections with Spatially-consistent Feature Learningcited by 26
- 2020Biases in Generative Art -- A Causal Look from the Lens of Art Historycited by 26
- 2016Detecting People in Artwork with CNNscited by 25
- 2022Semantic Segmentation in Art Paintingscited by 23
- 2018Can Computers Create Art?cited by 18
- 2020End-to-End Chinese Landscape Painting Creation Using Generative Adversarial Networkscited by 18
- 2020Increasing the Robustness of Semantic Segmentation Models with Painting-by-Numberscited by 17
- 2023Learning Causality-inspired Representation Consistency for Video Anomaly Detectioncited by 17
- 2020Content Masked Loss: Human-Like Brush Stroke Planning in a Reinforcement Learning Painting Agentcited by 15
- 2021Improving Object Detection in Art Images Using Only Style Transfercited by 15
- 2020Combining Semantic Guidance and Deep Reinforcement Learning For Generating Human Level Paintingscited by 13
- 2020Enhancing Human Pose Estimation in Ancient Vase Paintings via Perceptually-grounded Style Transfer Learningcited by 13
- 2022Domain Adaptation via Bidirectional Cross-Attention Transformercited by 13
- 2015The Cross-Depiction Problem: Computer Vision Algorithms for Recognising Objects in Artwork and in Photographscited by 10
- 2020Geometric Style Transfercited by 10
- 2023ARTxAI: Explainable Artificial Intelligence Curates Deep Representation Learning for Artistic Images using Fuzzy Techniquescited by 10
50 most cited of 84 All 84 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.