Özet
We propose a new approach for the problem of relative depth estimation from a single image. Instead of directly regressing over depth scores, we formulate the problem as estimation of a probability distribution over depth and aim to learn the parameters of the distributions which maximize the likelihood of the given data. To train our model, we propose a new ranking loss, Distributional Loss, which tries to increase the probability of farther pixel's depth being greater than the closer pixel's depth. Our proposed approach allows our model to output confidence in its estimation in the form of standard deviation of the distribution. We achieve state of the art results against a number of baselines while providing confidence in our estimations. Our analysis show that estimated confidence is actually a good indicator of accuracy. We investigate the usage of confidence information in a downstream task of metric depth estimation, to increase its performance.
Orijinal dil | İngilizce |
---|---|
Ana bilgisayar yayını başlığı | Proceedings - 2020 International Conference on 3D Vision, 3DV 2020 |
Yayınlayan | Institute of Electrical and Electronics Engineers Inc. |
Sayfalar | 1079-1088 |
Sayfa sayısı | 10 |
ISBN (Elektronik) | 9781728181288 |
DOI'lar | |
Yayın durumu | Yayınlandı - Kas 2020 |
Etkinlik | 8th International Conference on 3D Vision, 3DV 2020 - Virtual, Fukuoka, Japan Süre: 25 Kas 2020 → 28 Kas 2020 |
Yayın serisi
Adı | Proceedings - 2020 International Conference on 3D Vision, 3DV 2020 |
---|
???event.eventtypes.event.conference???
???event.eventtypes.event.conference??? | 8th International Conference on 3D Vision, 3DV 2020 |
---|---|
Ülke/Bölge | Japan |
Şehir | Virtual, Fukuoka |
Periyot | 25/11/20 → 28/11/20 |
Bibliyografik not
Publisher Copyright:© 2020 IEEE.