mlsanityData to 14 Oct 2026

Collaging Class-specific GANs for Semantic Image Synthesis

arXiv 2110.04281 ↗First posted 8 Oct 2021cs.CV cs.LGcited by 25

Not on the map. Why?

Abstract (arXiv)

We propose a new approach for high resolution semantic image synthesis. It consists of one base image generator and multiple class-specific generators. The base generator generates high quality images based on a segmentation map. To further improve the quality of different objects, we create a bank of Generative Adversarial Networks (GANs) by separately training class-specific models. This has several benefits including -- dedicated weights for each class; centrally aligned data for each model; additional training data from other sources, potential of higher resolution and quality; and easy manipulation of a specific object in the scene. Experiments show that our approach can generate high quality images in high resolution while having flexibility of object-level control by using class-specific generators.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Builds on 33 of its 42 references that are in the map. First posted on arXiv 8 Oct 2021.

Builds on

33 of 42 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  8. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  9. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  10. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  11. 2017Improved Training of Wasserstein GANscited by 2,235
  12. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
21 more
  1. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  2. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  3. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,179
  4. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  5. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 860
  6. 2017Wasserstein GANcited by 639
  7. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 628
  8. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 577
  9. 2018Image Generation from Scene Graphscited by 324
  10. 2018cGANs with Projection Discriminatorcited by 254
  11. 2019SEAN: Image Synthesis with Semantic Region-Adaptive Normalizationcited by 253
  12. 2020You Only Need Adversarial Supervision for Semantic Image Synthesiscited by 129
  13. 2019Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesiscited by 108
  14. 2017Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesiscited by 75
  15. 2019Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generationcited by 75
  16. 2019Mask-Guided Portrait Editing with Conditional GANscited by 61
  17. 2018FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discoverycited by 58
  18. 2021Style and Pose Control for Image Synthesis of Humans from a Single Monocular Viewcited by 53
  19. 2019Generating Multiple Objects at Spatially Distinct Locationscited by 41
  20. 2017LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generationcited by 36
  21. 2018Global and Local Consistent Age Generative Adversarial Networkscited by 12

Built on by

Cited by year

Citing papers per year: 2022: 11; 2023: 8; 2024: 4; 2025: 2.

25 papers.

Sort:

By area:

  1. 2023GLIGEN: Open-Set Grounded Text-to-Image Generationcited by 781
  2. 2022Semantic Image Synthesis via Diffusion Modelscited by 132
  3. 2022GIRAFFE HD: A High-Resolution 3D-aware Generative Modelcited by 86
  4. 2022InsetGAN for Full-Body Image Generationcited by 45
  5. 2023Sound to Visual Scene Generation by Audio-to-Visual Latent Alignmentcited by 41
  6. 2022BlobGAN: Spatially Disentangled Scene Representationscited by 35
  7. 2022TileGen: Tileable, Controllable Material Generation and Capturecited by 27
  8. 2024SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flowcited by 20
  9. 2023Audio Generation with Multiple Conditional Diffusion Modelcited by 18
  10. 2022Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesiscited by 15
  11. 2025X-Fusion: Introducing New Modality to Frozen Large Language Modelscited by 13
  12. 2023SIEDOB: Semantic Image Editing by Disentangling Object and Backgroundcited by 11
13 more
  1. 2022SCAM! Transferring humans between images with Semantic Cross Attention Modulationcited by 10
  2. 2023Semantic Image Synthesis via Class-Adaptive Cross-Attentioncited by 5
  3. 2022Synthesizing Photorealistic Virtual Humans Through Cross-modal Disentanglementcited by 4
  4. 2022Contrastive Learning for Diverse Disentangled Foreground Generationcited by 4
  5. 2023PICNN: A Pathway towards Interpretable Convolutional Neural Networkscited by 2
  6. 2024Automatic Scene Generation: State-of-the-Art Techniques, Models, Datasets, Challenges, and Future Prospectscited by 2
  7. 2025PARTE: Part-Guided Texturing for 3D Human Reconstruction from a Single Imagecited by 2
  8. 2022Discovering Class-Specific GAN Controls for Semantic Image Synthesiscited by 1
  9. 2023DiffBlender: Composable and Versatile Multimodal Text-to-Image Diffusion Modelscited by 1
  10. 2022Unifying conditional and unconditional semantic image synthesis with OCO-GANcited by 0
  11. 2023Variation-Aware Semantic Image Synthesiscited by 0
  12. 2024CIMGEN: Controlled Image Manipulation by Finetuning Pretrained Generative Models on Limited Datacited by 0
  13. 2024Task-Decoupled Image Inpainting Framework for Class-specific Object Removercited by 0