Datasets › Middlebury
Middlebury (Middlebury Stereo)
The Middlebury Stereo dataset consists of high-resolution stereo sequences with complex geometry and pixel-accurate ground-truth disparity data. The ground-truth disparities are acquired using a novel technique that employs structured lighting and does not require the calibration of the light projectors.
Source: https://vision.middlebury.edu/stereo/data/ Image Source: https://www.researchgate.net/figure/The-stereo-matching-results-on-the-Middlebury-dataset-From-left-to-right-each-set-of_fig3_273399625
Benchmarks archive 2025-07-28
All 5 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Video Frame Interpolation | Middlebury | IFRNet Interpolation Error 4.216 | IFRNet: Intermediate Feature Refine Network for... | ltkong218/ifrnet +1 | 11 | Compare |
| Stereo Image Super-Resolution | Middlebury - 4x upscaling | SwinFIRSSR PSNR 30.44 | SwinFIR: Revisiting the SwinIR with Fast Fourier... | Zdafeng/SwinFIR +1 | 9 | Compare |
| Stereo Image Super-Resolution | Middlebury - 2x upscaling | ASteISR PSNR 36.60 | ASteISR: Adapting Single Image Super-resolution... | fzuzyb/ASteISR | 9 | Compare |
| Image Super-Resolution | Middlebury - 2x upscaling | PASSRnet PSNR 34.05 | Learning Parallax Attention for Stereo Image Super-Resolution | LongguangWang/PASSRnet | 1 | Compare |
| Image Super-Resolution | Middlebury - 4x upscaling | PASSRnet PSNR 28.63 | Learning Parallax Attention for Stereo Image Super-Resolution | LongguangWang/PASSRnet | 1 | Compare |
Papers archive 2025-07-28
19 shown of 19 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 223. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
License archive 2025-07-28
Modalities archive 2025-07-28
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- Middlebury
- Middlebury - 2x upscaling
- Middlebury - 4x upscaling
3 variant names, as the archive lists them.
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