DiffSteISR: Harnessing diffusion prior for superior real-world stereo image super-resolution

Yuanbo Zhou, Xinlin Zhang, Wei Deng, Tao Wang, Tao Tan, Qinquan Gao, Tong Tong

Research output: Contribution to journalArticlepeer-review

Abstract

Although diffusion prior-based single-image super-resolution has demonstrated remarkable reconstruction capabilities, its potential in the domain of stereo image super-resolution remains underexplored. One significant challenge lies in the inherent stochasticity of diffusion models, which makes it difficult to ensure that the generated left and right images exhibit high semantic and texture consistency. This poses a considerable obstacle to advancing research in this field. Therefore, 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.

Original languageEnglish
Article number129437
JournalNeurocomputing
Volume623
DOIs
Publication statusPublished - 28 Mar 2025

Keywords

  • ControlNet
  • Diffusion model
  • Reconstructing
  • Stereo image super-resolution
  • Texture consistency

Fingerprint

Dive into the research topics of 'DiffSteISR: Harnessing diffusion prior for superior real-world stereo image super-resolution'. Together they form a unique fingerprint.

Cite this