TY - JOUR
T1 - DiffSteISR
T2 - Harnessing diffusion prior for superior real-world stereo image super-resolution
AU - Zhou, Yuanbo
AU - Zhang, Xinlin
AU - Deng, Wei
AU - Wang, Tao
AU - Tan, Tao
AU - Gao, Qinquan
AU - Tong, Tong
N1 - Publisher Copyright:
© 2025 Elsevier B.V.
PY - 2025/3/28
Y1 - 2025/3/28
N2 - 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.
AB - 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.
KW - ControlNet
KW - Diffusion model
KW - Reconstructing
KW - Stereo image super-resolution
KW - Texture consistency
UR - http://www.scopus.com/inward/record.url?scp=85215436634&partnerID=8YFLogxK
U2 - 10.1016/j.neucom.2025.129437
DO - 10.1016/j.neucom.2025.129437
M3 - Article
AN - SCOPUS:85215436634
SN - 0925-2312
VL - 623
JO - Neurocomputing
JF - Neurocomputing
M1 - 129437
ER -