BlendGAN: Learning and Blending the Internal Distributions of Single Images by Spatial Image-Identity Conditioning
Not on the map. Why?
Abstract (arXiv)
Training a generative model on a single image has drawn significant attention in recent years. Single image generative methods are designed to learn the internal patch distribution of a single natural image at multiple scales. These models can be used for drawing diverse samples that semantically resemble the training image, as well as for solving many image editing and restoration tasks that involve that particular image. Here, we introduce an extended framework, which allows to simultaneously learn the internal distributions of several images, by using a single model with spatially varying image-identity conditioning. Our BlendGAN opens the door to applications that are not supported by single-image models, including morphing, melding, and structure-texture fusion between two or more arbitrary images.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 24 of its 32 references that are in the map. First posted on arXiv 3 Dec 2022.
Builds on
24 of 32 references.
References · 24
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
- 2017Improved Training of Wasserstein GANscited by 2,223
- 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
- 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
- 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
- 2016Generative Visual Manipulation on the Natural Image Manifoldcited by 348
- 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
- 2016Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networkscited by 192
- 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
12 more
- 2020Improved Techniques for Training Single-Image GANscited by 77
- 2018Non-Stationary Texture Synthesis by Adversarial Expansioncited by 66
- 2017Learning Texture Manifolds with the Periodic Spatial GANcited by 53
- 2020Deep Geometric Texture Synthesiscited by 51
- 2016Texture Synthesis with Spatial Generative Adversarial Networkscited by 45
- 2020Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Samplecited by 43
- 2020TOAD-GAN: Coherent Style Level Generation from a Single Examplecited by 22
- 2021Few-shot Image Generation with Mixup-based Distance Learningcited by 16
- 2021Catch-A-Waveform: Learning to Generate Audio from a Single Short Examplecited by 15
- 2019Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texturecited by 14
- 2019Barycenters of Natural Images -- Constrained Wasserstein Barycenters for Image Morphingcited by 11
- 2020Learning Diagnosis of COVID-19 from a Single Radiological Imagecited by 2
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 1.
2 papers.