Ponku
Ponku
This is a continuation of the PR split (https://github.com/pytorch/vision/pull/6311, https://github.com/pytorch/vision/pull/6269) which contains the Sintel Stereo training dataset.
This PR is w.r.t. [Batteries Phase 3](https://github.com/pytorch/vision/issues/6323) proposal to add the [MaxVit](https://arxiv.org/abs/2204.01697) architecture. It is still a work in progress as it has yet to be trained. One caveat w.r.t....
This is a draft version for the [CREStereo](https://openaccess.thecvf.com/content/CVPR2022/papers/Li_Practical_Stereo_Matching_via_Cascaded_Recurrent_Network_With_Adaptive_Correlation_CVPR_2022_paper.pdf) model implementation. It's over-commented for easier readability for those that are unfamiliar with the paper. It also makes use of ModuleDicts and...
This is a continuation of the PR split (https://github.com/pytorch/vision/pull/6311, https://github.com/pytorch/vision/pull/6269) which contains the FallingThings dataset variants.
This is a continuation of the PR split (https://github.com/pytorch/vision/pull/6311, https://github.com/pytorch/vision/pull/6269) which contains the ETH3D low-res two-view dataset.
This is a continuation of the PR split (https://github.com/pytorch/vision/pull/6311, https://github.com/pytorch/vision/pull/6269) which contains the InStereo2k dataset.
This is a continuation of the PR split (https://github.com/pytorch/vision/pull/6311, https://github.com/pytorch/vision/pull/6269) which contains the CREStereo dataset.
This is a continuation of the PR split (https://github.com/pytorch/vision/pull/6311, https://github.com/pytorch/vision/pull/6269) which contains the Middlebury 2014 version dataset.
Added a Stereo Matching Dataset interface similar to the Optical Flow one. I believe we will need to have a renaming of datasets based on the task, at least for...
### 🚀 The feature The proposed feature aims to **extend the current datasets API** with datasets that are geared towards `the task of Stereo Matching`. It's main use case is...