Adaptive Super Resolution For One-Shot Talking-Head Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916173361184768 |
|---|---|
| author | Song, Luchuan Liu, Pinxin Yin, Guojun Xu, Chenliang |
| author_facet | Song, Luchuan Liu, Pinxin Yin, Guojun Xu, Chenliang |
| contents | The one-shot talking-head generation learns to synthesize a talking-head video with one source portrait image under the driving of same or different identity video. Usually these methods require plane-based pixel transformations via Jacobin matrices or facial image warps for novel poses generation. The constraints of using a single image source and pixel displacements often compromise the clarity of the synthesized images. Some methods try to improve the quality of synthesized videos by introducing additional super-resolution modules, but this will undoubtedly increase computational consumption and destroy the original data distribution. In this work, we propose an adaptive high-quality talking-head video generation method, which synthesizes high-resolution video without additional pre-trained modules. Specifically, inspired by existing super-resolution methods, we down-sample the one-shot source image, and then adaptively reconstruct high-frequency details via an encoder-decoder module, resulting in enhanced video clarity. Our method consistently improves the quality of generated videos through a straightforward yet effective strategy, substantiated by quantitative and qualitative evaluations. The code and demo video are available on: \url{https://github.com/Songluchuan/AdaSR-TalkingHead/}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_15944 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Adaptive Super Resolution For One-Shot Talking-Head Generation Song, Luchuan Liu, Pinxin Yin, Guojun Xu, Chenliang Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing The one-shot talking-head generation learns to synthesize a talking-head video with one source portrait image under the driving of same or different identity video. Usually these methods require plane-based pixel transformations via Jacobin matrices or facial image warps for novel poses generation. The constraints of using a single image source and pixel displacements often compromise the clarity of the synthesized images. Some methods try to improve the quality of synthesized videos by introducing additional super-resolution modules, but this will undoubtedly increase computational consumption and destroy the original data distribution. In this work, we propose an adaptive high-quality talking-head video generation method, which synthesizes high-resolution video without additional pre-trained modules. Specifically, inspired by existing super-resolution methods, we down-sample the one-shot source image, and then adaptively reconstruct high-frequency details via an encoder-decoder module, resulting in enhanced video clarity. Our method consistently improves the quality of generated videos through a straightforward yet effective strategy, substantiated by quantitative and qualitative evaluations. The code and demo video are available on: \url{https://github.com/Songluchuan/AdaSR-TalkingHead/}. |
| title | Adaptive Super Resolution For One-Shot Talking-Head Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing |
| url | https://arxiv.org/abs/2403.15944 |