TY - GEN
T1 - Estimating Image Depth in the Comics Domain
AU - Bhattacharjee, Deblina
AU - Everaert, Martin
AU - Salzmann, Mathieu
AU - Susstrunk, Sabine
PY - 2022/2/15
Y1 - 2022/2/15
N2 - Estimating the depth of comics images is challenging as such images a) are monocular; b) lack ground-truth depth annotations; c) differ across different artistic styles; d) are sparse and noisy. We thus, use an off-the-shelf unsupervised image to image translation method to translate the comics images to natural ones and then use an attention-guided monocular depth estimator to predict their depth. This lets us leverage the depth annotations of existing natural images to train the depth estimator. Furthermore, our model learns to distinguish between text and images in the comics panels to reduce text-based artefacts in the depth estimates. Our method consistently outperforms the existing state-of-the-art approaches across all metrics on both the DCM and eBDtheque images. Finally, we introduce a dataset to evaluate depth prediction on comics.
AB - Estimating the depth of comics images is challenging as such images a) are monocular; b) lack ground-truth depth annotations; c) differ across different artistic styles; d) are sparse and noisy. We thus, use an off-the-shelf unsupervised image to image translation method to translate the comics images to natural ones and then use an attention-guided monocular depth estimator to predict their depth. This lets us leverage the depth annotations of existing natural images to train the depth estimator. Furthermore, our model learns to distinguish between text and images in the comics panels to reduce text-based artefacts in the depth estimates. Our method consistently outperforms the existing state-of-the-art approaches across all metrics on both the DCM and eBDtheque images. Finally, we introduce a dataset to evaluate depth prediction on comics.
KW - Few-shot
KW - Semi- and Un- supervised Learning
KW - Vision Systems and Applications Transfer
UR - https://www.scopus.com/pages/publications/85126086312
U2 - 10.1109/wacv51458.2022.00118
DO - 10.1109/wacv51458.2022.00118
M3 - Chapter in a published conference proceeding
T3 - IEEE Workshop on Applications of Computer Vision (WACV)
SP - 1111
EP - 1120
BT - Proceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022
PB - IEEE
CY - U. S. A.
T2 - 22nd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022
Y2 - 4 January 2022 through 8 January 2022
ER -