M6-Fashion: High-Fidelity Multi-modal Image Generation and Editing
Not on the map. Why?
Abstract (arXiv)
The fashion industry has diverse applications in multi-modal image generation and editing. It aims to create a desired high-fidelity image with the multi-modal conditional signal as guidance. Most existing methods learn different condition guidance controls by introducing extra models or ignoring the style prior knowledge, which is difficult to handle multiple signal combinations and faces a low-fidelity problem. In this paper, we adapt both style prior knowledge and flexibility of multi-modal control into one unified two-stage framework, M6-Fashion, focusing on the practical AI-aided Fashion design. It decouples style codes in both spatial and semantic dimensions to guarantee high-fidelity image generation in the first stage. M6-Fashion utilizes self-correction for the non-autoregressive generation to improve inference speed, enhance holistic consistency, and support various signal controls. Extensive experiments on a large-scale clothing dataset M2C-Fashion demonstrate superior performances on various image generation and editing tasks. M6-Fashion model serves as a highly potential AI designer for the fashion industry.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 31 of its 44 references that are in the map. First posted on arXiv 24 May 2022.
Builds on
31 of 44 references.
References · 31
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2022Generative Adversarial Networkscited by 5,603
- 2021Zero-Shot Text-to-Image Generationcited by 4,276
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
- 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
- 2016Improved Techniques for Training GANscited by 2,938
- 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
19 more
- 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
- 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
- 2021Alias-Free Generative Adversarial Networkscited by 1,181
- 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
- 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
- 2021CogView: Mastering Text-to-Image Generation via Transformerscited by 691
- 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
- 2021Designing an Encoder for StyleGAN Image Manipulationcited by 542
- 2020Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Imagescited by 261
- 2019Controllable Text-to-Image Generationcited by 187
- 2019Self-Correction for Human Parsingcited by 179
- 2021M6: A Chinese Multimodal Pretrainercited by 91
- 2021Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editingcited by 91
- 2020Incorporating BERT into Parallel Sequence Decoding with Adapterscited by 39
- 2021M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformerscited by 36
- 2020Probabilistically Masked Language Model Capable of Autoregressive Generation in Arbitrary Word Ordercited by 28
- 2019A Generalized Framework of Sequence Generation with Application to Undirected Sequence Modelscited by 17
- 2020TediGAN: Text-Guided Diverse Face Image Generation and Manipulationcited by 11
- 2021Super-Resolving Cross-Domain Face Miniatures by Peeking at One-Shot Exemplarcited by 5
Built on by
Citing papers per year: 2022: 1; 2023: 1; 2024: 1.
3 papers.