Papers › ASteISR: Adapting Single Image Super-resolution Pre-trained Model for Efficient Stereo...

ASteISR: Adapting Single Image Super-resolution Pre-trained Model for Efficient Stereo Image Super-resolution

4 Jul 2024arXiv:2407.03598archive 2025-07-28

Yuanbo Zhou, Yuyang Xue, Wei Deng, Xinlin Zhang, Qinquan Gao, Tong Tong

Despite advances in the paradigm of pre-training then fine-tuning in low-level vision tasks, significant challenges persist particularly regarding the increased size of pre-trained models such as memory usage and training time. Another concern often encountered is the unsatisfying results yielded when directly applying pre-trained single-image models to multi-image domain. In this paper, we propose a efficient method for transferring a pre-trained single-image super-resolution (SISR) transformer network to the domain of stereo image super-resolution (SteISR) through a parameter-efficient fine-tuning (PEFT) method. Specifically, we introduce the concept of stereo adapters and spatial adapters which are incorporated into the pre-trained SISR transformer network. Subsequently, the pre-trained SISR model is frozen, enabling us to fine-tune the adapters using stereo datasets along. By adopting this training method, we enhance the ability of the SISR model to accurately infer stereo images by 0.79dB on the Flickr1024 dataset. This method allows us to train only 4.8% of the original model parameters, achieving state-of-the-art performance on four commonly used SteISR benchmarks. Compared to the more complicated full fine-tuning approach, our method reduces training time and memory consumption by 57% and 15%, respectively.

PaperPDFCode

Code

fzuzyb/ASteISR officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Super-ResolutionStereo Image Super-ResolutionSuper-Resolutionparameter-efficient fine-tuning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Stereo Image Super-Resolution Flickr1024 - 2x upscaling ASteISR PSNR 30.33 #1 of 10 Archive leaderboard report
Stereo Image Super-Resolution KITTI2012 - 2x upscaling ASteISR PSNR 31.86 #1 of 5 Archive leaderboard report
Stereo Image Super-Resolution KITTI2015 - 2x upscaling ASteISR PSNR 31.48 #1 of 9 Archive leaderboard report
Stereo Image Super-Resolution Middlebury - 2x upscaling ASteISR PSNR 36.60 #1 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections