High Resolution Multi-Scale RAFT (Robust Vision Challenge 2022)
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918036892549120 |
|---|---|
| author | Jahedi, Azin Luz, Maximilian Mehl, Lukas Rivinius, Marc Bruhn, Andrés |
| author_facet | Jahedi, Azin Luz, Maximilian Mehl, Lukas Rivinius, Marc Bruhn, Andrés |
| contents | In this report, we present our optical flow approach, MS-RAFT+, that won the Robust Vision Challenge 2022. It is based on the MS-RAFT method, which successfully integrates several multi-scale concepts into single-scale RAFT. Our approach extends this method by exploiting an additional finer scale for estimating the flow, which is made feasible by on-demand cost computation. This way, it can not only operate at half the original resolution, but also use MS-RAFT's shared convex upsampler to obtain full resolution flow. Moreover, our approach relies on an adjusted fine-tuning scheme during training. This in turn aims at improving the generalization across benchmarks. Among all participating methods in the Robust Vision Challenge, our approach ranks first on VIPER and second on KITTI, Sintel, and Middlebury, resulting in the first place of the overall ranking. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2210_16900 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | High Resolution Multi-Scale RAFT (Robust Vision Challenge 2022) Jahedi, Azin Luz, Maximilian Mehl, Lukas Rivinius, Marc Bruhn, Andrés Computer Vision and Pattern Recognition In this report, we present our optical flow approach, MS-RAFT+, that won the Robust Vision Challenge 2022. It is based on the MS-RAFT method, which successfully integrates several multi-scale concepts into single-scale RAFT. Our approach extends this method by exploiting an additional finer scale for estimating the flow, which is made feasible by on-demand cost computation. This way, it can not only operate at half the original resolution, but also use MS-RAFT's shared convex upsampler to obtain full resolution flow. Moreover, our approach relies on an adjusted fine-tuning scheme during training. This in turn aims at improving the generalization across benchmarks. Among all participating methods in the Robust Vision Challenge, our approach ranks first on VIPER and second on KITTI, Sintel, and Middlebury, resulting in the first place of the overall ranking. |
| title | High Resolution Multi-Scale RAFT (Robust Vision Challenge 2022) |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2210.16900 |