StereoDiffusion: Training-Free Stereo Image Generation Using Latent Diffusion Models
This addresses the demand for stereo images in XR applications, but it is incremental as it builds on existing latent diffusion models.
The paper tackles the problem of generating stereo images for XR devices by introducing StereoDiffusion, a training-free method that integrates into Stable Diffusion to produce stereo image pairs, achieving state-of-the-art scores in quantitative evaluations.
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.