Data to 14 Oct 2026

Image Processing Using Multi-Code GAN Prior

arXiv 1912.07116 ↗First posted 15 Dec 2019cs.CVcited by 185

Not on the map. Why?

Cited by 36 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Despite the success of Generative Adversarial Networks (GANs) in image synthesis, applying trained GAN models to real image processing remains challenging. Previous methods typically invert a target image back to the latent space either by back-propagation or by learning an additional encoder. However, the reconstructions from both of the methods are far from ideal. In this work, we propose a novel approach, called mGANprior, to incorporate the well-trained GANs as effective prior to a variety of image processing tasks. In particular, we employ multiple latent codes to generate multiple feature maps at some intermediate layer of the generator, then compose them with adaptive channel importance to recover the input image. Such an over-parameterization of the latent space significantly improves the image reconstruction quality, outperforming existing competitors. The resulting high-fidelity image reconstruction enables the trained GAN models as prior to many real-world applications, such as image colorization, super-resolution, image inpainting, and semantic manipulation. We further analyze the properties of the layer-wise representation learned by GAN models and shed light on what knowledge each layer is capable of representing.

Key facts. Cited by 185 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 50; 2022: 62; 2023: 34; 2024: 23; 2025: 12; 2026: 4.

185 papers.

Sort:

By area:

2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
2021Alias-Free Generative Adversarial Networkscited by 1,184
2022Denoising Diffusion Restoration Modelscited by 963
2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 642
2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 635
2023Zero-shot Image-to-Image Translationcited by 505
2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 489
2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 370
2021GAN Inversion: A Surveycited by 367
2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 349
2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 286

38 more

2022Towards Robust Blind Face Restoration with Codebook Lookup Transformercited by 231
2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
2023Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Modelscited by 203
2023Generative Diffusion Prior for Unified Image Restoration and Enhancementcited by 199
2021GAN Prior Embedded Network for Blind Face Restoration in the Wildcited by 197
2021High-Fidelity GAN Inversion for Image Attribute Editingcited by 197
2021Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalizationcited by 141
2021Generative Adversarial Transformerscited by 120
2022VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decodercited by 116
20213D-aware Image Synthesis via Learning Structural and Textural Representationscited by 109
2022Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priorscited by 100
2023AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusioncited by 100
2023Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion Modelscited by 99
2022DifFace: Blind Face Restoration with Diffused Error Contractioncited by 97
2024Arbitrary-steps Image Super-resolution via Diffusion Inversioncited by 86
2022RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairscited by 85
2023Domain-Agnostic Tuning-Encoder for Fast Personalization of Text-To-Image Modelscited by 85
2021Unsupervised 3D Shape Completion through GAN Inversioncited by 70
2022Stitch it in Time: GAN-Based Facial Editing of Real Videoscited by 68
2023A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AIcited by 68
2023CoSeR: Bridging Image and Language for Cognitive Super-Resolutioncited by 66
2022High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimizationcited by 65
2024Efficient Diffusion Model for Image Restoration by Residual Shiftingcited by 64
2023Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolutioncited by 59
2022High-resolution Face Swapping via Latent Semantics Disentanglementcited by 57
2022Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Networkcited by 57
2021Using latent space regression to analyze and leverage compositionality in GANscited by 55
2021Towards Vivid and Diverse Image Colorization with Generative Color Priorcited by 55
2021GAN Inversion for Out-of-Range Images with Geometric Transformationscited by 55
2022TAPE: Task-Agnostic Prior Embedding for Image Restorationcited by 55
2021Anycost GANs for Interactive Image Synthesis and Editingcited by 54
2022Third Time's the Charm? Image and Video Editing with StyleGAN3cited by 54
2023PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidancecited by 49
2024Deep Learning-based Image and Video Inpainting: A Surveycited by 44
2021Reflash Dropout in Image Super-Resolutioncited by 41
2024XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolutioncited by 41
2023Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Modelscited by 40
2021Image-Based CLIP-Guided Essence Transfercited by 39

50 most cited of 185 All 185 (JSON)