mlsanityData to 7 Oct 2026

Anycost GANs for Interactive Image Synthesis and Editing

arXiv 2103.03243 ↗First posted 4 Mar 2021cs.CVcited by 54

Not on the map. Why?

Abstract (arXiv)

Generative adversarial networks (GANs) have enabled photorealistic image synthesis and editing. However, due to the high computational cost of large-scale generators (e.g., StyleGAN2), it usually takes seconds to see the results of a single edit on edge devices, prohibiting interactive user experience. In this paper, we take inspirations from modern rendering software and propose Anycost GAN for interactive natural image editing. We train the Anycost GAN to support elastic resolutions and channels for faster image generation at versatile speeds. Running subsets of the full generator produce outputs that are perceptually similar to the full generator, making them a good proxy for preview. By using sampling-based multi-resolution training, adaptive-channel training, and a generator-conditioned discriminator, the anycost generator can be evaluated at various configurations while achieving better image quality compared to separately trained models. Furthermore, we develop new encoder training and latent code optimization techniques to encourage consistency between the different sub-generators during image projection. Anycost GAN can be executed at various cost budgets (up to 10x computation reduction) and adapt to a wide range of hardware and latency requirements. When deployed on desktop CPUs and edge devices, our model can provide perceptually similar previews at 6-12x speedup, enabling interactive image editing. The code and demo are publicly available: https://github.com/mit-han-lab/anycost-gan.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). Builds on 71 of its 83 references that are in the map. First posted on arXiv 4 Mar 2021.

Builds on

71 of 83 references.

References · 71

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  9. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  10. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  11. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  12. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
38 more
  1. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  2. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  3. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  4. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  5. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  6. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  7. 2019Searching for MobileNetV3cited by 1,984
  8. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  9. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  10. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  11. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  12. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  13. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  14. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  15. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  16. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  17. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  18. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  19. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  20. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  21. 2018Self-Attention Generative Adversarial Networkscited by 809
  22. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  23. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  24. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 697
  25. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
  26. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  27. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  28. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 666
  29. 2020GANSpace: Discovering Interpretable GAN Controlscited by 612
  30. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  31. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
  32. 2016Learning Structured Sparsity in Deep Neural Networkscited by 538
  33. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 426
  34. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  35. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 411
  36. 2018AMC: AutoML for Model Compression and Acceleration on Mobile Devicescited by 375
  37. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  38. 2017Universal Style Transfer via Feature Transformscited by 352

50 most cited of 71 All 71 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 14; 2023: 16; 2024: 7; 2025: 6; 2026: 2.

54 papers.

Sort:

By area:

  1. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  2. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 300
  3. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 251
  4. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  5. 2023Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Modelscited by 131
  6. 2022Any-resolution Training for High-resolution Image Synthesiscited by 72
  7. 2021Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codescited by 71
  8. 2023Discovering Interpretable Directions in the Semantic Latent Space of Diffusion Modelscited by 60
  9. 2022Third Time's the Charm? Image and Video Editing with StyleGAN3cited by 54
  10. 2021Ensembling with Deep Generative Viewscited by 53
  11. 20223D GAN Inversion with Pose Optimizationcited by 44
  12. 2022Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Modelscited by 44
38 more
  1. 2023Attribute-preserving Face Dataset Anonymization via Latent Code Optimizationcited by 43
  2. 2022Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face Recognitioncited by 42
  3. 2022State-of-the-Art in the Architecture, Methods and Applications of StyleGANcited by 34
  4. 2022Few-shot Image Generation via Adaptation-Aware Kernel Modulationcited by 33
  5. 2021Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Schemecited by 23
  6. 2021High Resolution Face Editing with Masked GAN Latent Code Optimizationcited by 21
  7. 2021LTT-GAN: Looking Through Turbulence by Inverting GANscited by 21
  8. 2023Exploring Incompatible Knowledge Transfer in Few-shot Image Generationcited by 19
  9. 2023Image-Based Virtual Try-On: A Surveycited by 19
  10. 2022Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpointcited by 18
  11. 2022Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesiscited by 12
  12. 2023From Posterior Sampling to Meaningful Diversity in Image Restorationcited by 12
  13. 2023Scalable Face Image Coding via StyleGAN Prior: Towards Compression for Human-Machine Collaborative Visioncited by 11
  14. 2022BareSkinNet: De-makeup and De-lighting via 3D Face Reconstructioncited by 10
  15. 2023What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networkcited by 10
  16. 2024MM2Latent: Text-to-facial image generation and editing in GANs with multimodal assistancecited by 7
  17. 2023Child Face Recognition at Scale: Synthetic Data Generation and Performance Benchmarkcited by 6
  18. 2022PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generationcited by 5
  19. 2025Scalable GANs with Transformerscited by 5
  20. 2025Neon: Negative Extrapolation From Self-Training Improves Image Generationcited by 5
  21. 2022Discriminator-Cooperated Feature Map Distillation for GAN Compressioncited by 4
  22. 2024Stylized Face Sketch Extraction via Generative Prior with Limited Datacited by 4
  23. 2024Hierarchical Uncertainty Exploration via Feedforward Posterior Treescited by 4
  24. 2025Enhancing Close-up Novel View Synthesis via Pseudo-labelingcited by 4
  25. 2023Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifoldcited by 3
  26. 2024StyleCineGAN: Landscape Cinemagraph Generation using a Pre-trained StyleGANcited by 3
  27. 2024Synthetic Medical Imaging Generation with Generative Adversarial Networks For Plain Radiographscited by 3
  28. 2023Region-Aware Portrait Retouching with Sparse Interactive Guidancecited by 2
  29. 2025Do DeepFake Attribution Models Generalize?cited by 2
  30. 2022Exploring Content Relationships for Distilling Efficient GANscited by 1
  31. 2023AdAM: Few-Shot Image Generation via Adaptation-Aware Kernel Modulationcited by 1
  32. 2023Interactive Neural Paintingcited by 1
  33. 2024Early Stopping Criteria for Training Generative Adversarial Networks in Biomedical Imagingcited by 1
  34. 2021DGL-GAN: Discriminator Guided Learning for GAN Compressioncited by 0
  35. 2022Towards Device Efficient Conditional Image Generationcited by 0
  36. 2023Efficient Scale-Invariant Generator with Column-Row Entangled Pixel Synthesiscited by 0
  37. 2023A Unified Compression Framework for Efficient Speech-Driven Talking-Face Generationcited by 0
  38. 2024Detecting Face Synthesis Using a Concealed Fusion Modelcited by 0

50 most cited of 54 All 54 (JSON)