StereoDiffusion: Training-Free Stereo Image Generation Using Latent Diffusion Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916551498661888 |
|---|---|
| author | Wang, Lezhong Frisvad, Jeppe Revall Jensen, Mark Bo Bigdeli, Siavash Arjomand |
| author_facet | Wang, Lezhong Frisvad, Jeppe Revall Jensen, Mark Bo Bigdeli, Siavash Arjomand |
| contents | The demand for stereo images increases as manufacturers launch more XR devices. To meet this demand, we introduce StereoDiffusion, a method that, unlike traditional inpainting pipelines, is trainning free, remarkably straightforward to use, and it seamlessly integrates into the original Stable Diffusion model. Our method modifies the latent variable to provide an end-to-end, lightweight capability for fast generation of stereo image pairs, without the need for fine-tuning model weights or any post-processing of images. Using the original input to generate a left image and estimate a disparity map for it, we generate the latent vector for the right image through Stereo Pixel Shift operations, complemented by Symmetric Pixel Shift Masking Denoise and Self-Attention Layers Modification methods to align the right-side image with the left-side image. Moreover, our proposed method maintains a high standard of image quality throughout the stereo generation process, achieving state-of-the-art scores in various quantitative evaluations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_04965 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | StereoDiffusion: Training-Free Stereo Image Generation Using Latent Diffusion Models Wang, Lezhong Frisvad, Jeppe Revall Jensen, Mark Bo Bigdeli, Siavash Arjomand Computer Vision and Pattern Recognition Artificial Intelligence The demand for stereo images increases as manufacturers launch more XR devices. To meet this demand, we introduce StereoDiffusion, a method that, unlike traditional inpainting pipelines, is trainning free, remarkably straightforward to use, and it seamlessly integrates into the original Stable Diffusion model. Our method modifies the latent variable to provide an end-to-end, lightweight capability for fast generation of stereo image pairs, without the need for fine-tuning model weights or any post-processing of images. Using the original input to generate a left image and estimate a disparity map for it, we generate the latent vector for the right image through Stereo Pixel Shift operations, complemented by Symmetric Pixel Shift Masking Denoise and Self-Attention Layers Modification methods to align the right-side image with the left-side image. Moreover, our proposed method maintains a high standard of image quality throughout the stereo generation process, achieving state-of-the-art scores in various quantitative evaluations. |
| title | StereoDiffusion: Training-Free Stereo Image Generation Using Latent Diffusion Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2403.04965 |