D. Ignatov, A. Ignatov, R. Timofte.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 6177-6186, 2024.

• Virtually augmented NYU Depth V2 training dataset (ANYU) extended with 10% and 100% artificially modified images
• Virtually enriched (100 %) NYU Depth V2 test set: 2048 artificially modified RGB-D testing pairs of images
• Checkpoint of the VPD model: RMSE 0.2478

Since the ANYU dataset contains RGB-D images from NYU depth v2, along with our paper [1] the original NYU article [2] should be cited:

@inproceedings{Ignatov:CVPR24, author = {Ignatov, Dmitry and Ignatov, Andrey and Timofte, Radu}, title = {Virtually Enriched NYU Depth V2 Dataset for Monocular Depth Estimation: Do We Need Artificial Augmentation?}, booktitle = {CVPR}, year = {2024}}

@inproceedings{Silberman:ECCV12, author = {Silberman, Nathan and Hoiem, Derek and Kohli, Pushmeet and Fergus, Rob}, title = {Indoor Segmentation and Support Inference from RGBD Images}, booktitle = {ECCV}, year = {2012} }