Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.17143 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913486534082560 |
|---|---|
| author | Kubiak, Nikolina Wortman, Elliot Mustafa, Armin Phillipson, Graeme Jolly, Stephen Hadfield, Simon |
| author_facet | Kubiak, Nikolina Wortman, Elliot Mustafa, Armin Phillipson, Graeme Jolly, Stephen Hadfield, Simon |
| contents | Existing shadow detection models struggle to differentiate dark image areas from shadows. In this paper, we tackle this issue by verifying that all detected shadows are real, i.e. they have paired shadow casters. We perform this step in a physically-accurate manner by differentiably re-rendering the scene and observing the changes stemming from carving out estimated shadow casters. Thanks to this approach, the RenDetNet proposed in this paper is the first learning-based shadow detection model whose supervisory signals can be computed in a self-supervised manner. The developed system compares favourably against recent models trained on our data. As part of this publication, we release our code on github. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_17143 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RenDetNet: Weakly-supervised Shadow Detection with Shadow Caster Verification Kubiak, Nikolina Wortman, Elliot Mustafa, Armin Phillipson, Graeme Jolly, Stephen Hadfield, Simon Computer Vision and Pattern Recognition Graphics Existing shadow detection models struggle to differentiate dark image areas from shadows. In this paper, we tackle this issue by verifying that all detected shadows are real, i.e. they have paired shadow casters. We perform this step in a physically-accurate manner by differentiably re-rendering the scene and observing the changes stemming from carving out estimated shadow casters. Thanks to this approach, the RenDetNet proposed in this paper is the first learning-based shadow detection model whose supervisory signals can be computed in a self-supervised manner. The developed system compares favourably against recent models trained on our data. As part of this publication, we release our code on github. |
| title | RenDetNet: Weakly-supervised Shadow Detection with Shadow Caster Verification |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2408.17143 |