LATENTPATCH: A Non-Parametric Approach for Face Generation and Editing
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914659138797568 |
|---|---|
| author | Samuth, Benjamin Rabin, Julien Tschumperlé, David Jurie, Frédéric |
| author_facet | Samuth, Benjamin Rabin, Julien Tschumperlé, David Jurie, Frédéric |
| contents | This paper presents LatentPatch, a new method for generating realistic images from a small dataset of only a few images. We use a lightweight model with only a few thousand parameters. Unlike traditional few-shot generation methods that finetune pre-trained large-scale generative models, our approach is computed directly on the latent distribution by sequential feature matching, and is explainable by design. Avoiding large models based on transformers, recursive networks, or self-attention, which are not suitable for small datasets, our method is inspired by non-parametric texture synthesis and style transfer models, and ensures that generated image features are sampled from the source distribution. We extend previous single-image models to work with a few images and demonstrate that our method can generate realistic images, as well as enable conditional sampling and image editing. We conduct experiments on face datasets and show that our simplistic model is effective and versatile. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_16830 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LATENTPATCH: A Non-Parametric Approach for Face Generation and Editing Samuth, Benjamin Rabin, Julien Tschumperlé, David Jurie, Frédéric Multimedia Image and Video Processing Signal Processing This paper presents LatentPatch, a new method for generating realistic images from a small dataset of only a few images. We use a lightweight model with only a few thousand parameters. Unlike traditional few-shot generation methods that finetune pre-trained large-scale generative models, our approach is computed directly on the latent distribution by sequential feature matching, and is explainable by design. Avoiding large models based on transformers, recursive networks, or self-attention, which are not suitable for small datasets, our method is inspired by non-parametric texture synthesis and style transfer models, and ensures that generated image features are sampled from the source distribution. We extend previous single-image models to work with a few images and demonstrate that our method can generate realistic images, as well as enable conditional sampling and image editing. We conduct experiments on face datasets and show that our simplistic model is effective and versatile. |
| title | LATENTPATCH: A Non-Parametric Approach for Face Generation and Editing |
| topic | Multimedia Image and Video Processing Signal Processing |
| url | https://arxiv.org/abs/2401.16830 |