Add CC BY-NC 4.0 LICENSE file with attribution scope
Browse files
LICENSE
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
This work is licensed under the
|
| 2 |
+
Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).
|
| 3 |
+
|
| 4 |
+
To view a copy of this license, visit
|
| 5 |
+
https://creativecommons.org/licenses/by-nc/4.0/legalcode
|
| 6 |
+
or send a letter to Creative Commons, PO Box 1866, Mountain View, CA 94042, USA.
|
| 7 |
+
|
| 8 |
+
Summary of terms:
|
| 9 |
+
- You are free to share and adapt this work for non-commercial purposes,
|
| 10 |
+
provided you give appropriate credit.
|
| 11 |
+
- Commercial use is NOT permitted.
|
| 12 |
+
- No additional restrictions may be imposed beyond what this license requires.
|
| 13 |
+
|
| 14 |
+
------------------------------------------------------------------------------
|
| 15 |
+
Scope
|
| 16 |
+
------------------------------------------------------------------------------
|
| 17 |
+
|
| 18 |
+
This license applies to the model weights distributed in this repository
|
| 19 |
+
(model.safetensors and config.yaml). The released weights are derivative
|
| 20 |
+
works of:
|
| 21 |
+
|
| 22 |
+
(a) The Depth Anything 3 "da3-giant" backbone
|
| 23 |
+
(https://github.com/ByteDance-Seed/Depth-Anything-3), released by
|
| 24 |
+
ByteDance Ltd. under CC BY-NC 4.0.
|
| 25 |
+
|
| 26 |
+
(b) Training on the PanoInfinigen dataset
|
| 27 |
+
(https://huggingface.co/datasets/prs-eth/PanoInfinigen). The "urban"
|
| 28 |
+
split of that dataset was rendered from scenes generated with the
|
| 29 |
+
iCity Blender addon by Hothifa Smair
|
| 30 |
+
(https://superhivemarket.com/products/icity), and is used here under
|
| 31 |
+
written authorization for non-commercial academic research from the
|
| 32 |
+
iCity author.
|
| 33 |
+
|
| 34 |
+
PaGeR is the work of Vukasin Bozic et al. at the Photogrammetry and Remote
|
| 35 |
+
Sensing Lab (PRS), ETH Zürich, 2026.
|