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
Variants: Middlebury, Middlebury - 2x upscaling, Middlebury - 4x upscaling
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Video Frame Interpolation | IFRNet | IFRNet: Intermediate Feature Refine Network … | 2022-05-29 |
| Video Frame Interpolation | MA-CSPA | Exploring Motion Ambiguity and Alignment … | 2022-03-19 |
| Video Frame Interpolation | FILM | FILM: Frame Interpolation for Large … | 2022-02-10 |
| Video Frame Interpolation | CDFI | CDFI: Compression-Driven Network Design for … | 2021-03-18 |
| Video Frame Interpolation | BMBC | BMBC:Bilateral Motion Estimation with Bilateral … | 2020-07-17 |
| Video Frame Interpolation | SoftSplat | Softmax Splatting for Video Frame … | 2020-03-11 |
| Video Frame Interpolation | DAIN | Depth-Aware Video Frame Interpolation | 2019-04-01 |
| Video Frame Interpolation | MEMC-NET | MEMC-Net: Motion Estimation and Motion … | 2018-10-20 |
| Video Frame Interpolation | ToFlow | Video Enhancement with Task-Oriented Flow | 2017-11-24 |
| Video Frame Interpolation | SepConv-L1 | Video Frame Interpolation via Adaptive … | 2017-08-05 |
Recent papers with results on this dataset: