DIffSteISR: Harnessing Diffusion Prior for Superior Real-world Stereo Image Super-Resolution

TL;DR

DiffSteISR is a novel diffusion-based framework that leverages pre-trained models and specialized attention mechanisms to enhance the quality and consistency of super-resolved real-world stereo images, outperforming previous methods.

Contribution

The paper introduces DiffSteISR, integrating TASCATA, SOA ControlNet, and SSE to improve texture detail, semantic accuracy, and view consistency in stereo image super-resolution.

Findings

Achieves high texture fidelity in super-resolved stereo images.

Maintains strong semantic and texture consistency between views.

Outperforms existing methods in reconstructing natural stereo images.

Abstract

We introduce DiffSteISR, a pioneering framework for reconstructing real-world stereo images. DiffSteISR utilizes the powerful prior knowledge embedded in pre-trained text-to-image model to efficiently recover the lost texture details in low-resolution stereo images. Specifically, DiffSteISR implements a time-aware stereo cross attention with temperature adapter (TASCATA) to guide the diffusion process, ensuring that the generated left and right views exhibit high texture consistency thereby reducing disparity error between the super-resolved images and the ground truth (GT) images. Additionally, a stereo omni attention control network (SOA ControlNet) is proposed to enhance the consistency of super-resolved images with GT images in the pixel, perceptual, and distribution space. Finally, DiffSteISR incorporates a stereo semantic extractor (SSE) to capture unique viewpoint soft semantic information and shared hard tag semantic information, thereby effectively improving the semantic accuracy and consistency of the generated left and right images. Extensive experimental results demonstrate that DiffSteISR accurately reconstructs natural and precise textures from low-resolution stereo images while maintaining a high consistency of semantic and texture between the left and right views.