You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+18-18Lines changed: 18 additions & 18 deletions
Original file line number
Diff line number
Diff line change
@@ -14,31 +14,31 @@ and our [preprint](https://arxiv.org/abs/2103.13413):
14
14
15
15
MiDaS was trained on 10 datasets (ReDWeb, DIML, Movies, MegaDepth, WSVD, TartanAir, HRWSI, ApolloScape, BlendedMVS, IRS) with
16
16
multi-objective optimization.
17
-
The original model that was trained on 5 datasets (`MIX 5` in the paper) can be found [here](https://github.com/intel-isl/MiDaS/releases/tag/v2).
17
+
The original model that was trained on 5 datasets (`MIX 5` in the paper) can be found [here](https://github.com/isl-org/MiDaS/releases/tag/v2).
18
18
19
19
20
20
### Changelog
21
21
*[Sep 2021] Integrated to [Huggingface Spaces](https://huggingface.co/spaces) with [Gradio](https://github.com/gradio-app/gradio). See [Gradio Web Demo](https://huggingface.co/spaces/akhaliq/DPT-Large).
22
22
*[Apr 2021] Released MiDaS v3.0:
23
23
- New models based on [Dense Prediction Transformers](https://arxiv.org/abs/2103.13413) are on average [21% more accurate](#Accuracy) than MiDaS v2.1
24
-
- Additional models can be found [here](https://github.com/intel-isl/DPT)
24
+
- Additional models can be found [here](https://github.com/isl-org/DPT)
25
25
*[Nov 2020] Released MiDaS v2.1:
26
-
- New model that was trained on 10 datasets and is on average about [10% more accurate](#Accuracy) than [MiDaS v2.0](https://github.com/intel-isl/MiDaS/releases/tag/v2)
27
-
- New light-weight model that achieves [real-time performance](https://github.com/intel-isl/MiDaS/tree/master/mobile) on mobile platforms.
28
-
- Sample applications for [iOS](https://github.com/intel-isl/MiDaS/tree/master/mobile/ios) and [Android](https://github.com/intel-isl/MiDaS/tree/master/mobile/android)
29
-
- [ROS package](https://github.com/intel-isl/MiDaS/tree/master/ros) for easy deployment on robots
26
+
- New model that was trained on 10 datasets and is on average about [10% more accurate](#Accuracy) than [MiDaS v2.0](https://github.com/isl-org/MiDaS/releases/tag/v2)
27
+
- New light-weight model that achieves [real-time performance](https://github.com/isl-org/MiDaS/tree/master/mobile) on mobile platforms.
28
+
- Sample applications for [iOS](https://github.com/isl-org/MiDaS/tree/master/mobile/ios) and [Android](https://github.com/isl-org/MiDaS/tree/master/mobile/android)
29
+
- [ROS package](https://github.com/isl-org/MiDaS/tree/master/ros) for easy deployment on robots
30
30
*[Jul 2020] Added TensorFlow and ONNX code. Added [online demo](http://35.202.76.57/).
31
31
*[Dec 2019] Released new version of MiDaS - the new model is significantly more accurate and robust
32
-
*[Jul 2019] Initial release of MiDaS ([Link](https://github.com/intel-isl/MiDaS/releases/tag/v1))
32
+
*[Jul 2019] Initial release of MiDaS ([Link](https://github.com/isl-org/MiDaS/releases/tag/v1))
33
33
34
34
### Setup
35
35
36
36
1) Pick one or more models and download corresponding weights to the `weights` folder:
37
37
38
-
- For highest quality: [dpt_large](https://github.com/intel-isl/DPT/releases/download/1_0/dpt_large-midas-2f21e586.pt)
39
-
- For moderately less quality, but better speed on CPU and slower GPUs: [dpt_hybrid](https://github.com/intel-isl/DPT/releases/download/1_0/dpt_hybrid-midas-501f0c75.pt)
40
-
- For real-time applications on resource-constrained devices: [midas_v21_small](https://github.com/AlexeyAB/MiDaS/releases/download/midas_dpt/midas_v21_small-70d6b9c8.pt)
- For highest quality: [dpt_large](https://github.com/isl-org/MiDaS/releases/download/v3/dpt_large-midas-2f21e586.pt)
39
+
- For moderately less quality, but better speed on CPU and slower GPUs: [dpt_hybrid](https://github.com/isl-org/MiDaS/releases/download/v3/dpt_hybrid-midas-501f0c75.pt)
40
+
- For real-time applications on resource-constrained devices: [midas_v21_small](https://github.com/isl-org/MiDaS/releases/download/v2_1/midas_v21_small-70d6b9c8.pt)
0 commit comments