update docs

docs/docfx.json

@@ -51,7 +51,8 @@
     "globalMetadata": {
       "_appFaviconPath": "images/favicon.ico",
       "_appLogoPath": "images/doji.png",
-      "_appLogoUrl": "https://www.doji-tech.com/"
+      "_appLogoUrl": "https://www.doji-tech.com/",
+      "_disableContribution": true
     },
     "fileMetadataFiles": [],
     "template": [

docs/index.md

@@ -2,4 +2,8 @@
 
 [Midas][1] unlocks real-time monocular depth estimation with MiDaS models running in Unity Sentis.
 
+To get started, please see the [Getting Started](manual/getting-started.md) page. The package also provides a number of samples that can be imported via the Package Manager.
+
+![banner](./images/banner.webp)
+
 [1]: https://assetstore.unity.com/packages/slug/268501

docs/manual/getting-started.md

@@ -2,50 +2,66 @@
 
 This page will cover the basics of using the Midas package.
 
+
 ## Basic Usage
 
+To start, create a new 'Midas' instance:
+
 ```CSharp
-using UnityEngine;
+var midas = new Midas();
+```
 
-public class DepthEstimationExample : MonoBehaviour {
-    public Texture inputImage;
-    public Midas midasInstance;
+Then you can pass in a Texture2D to @Midas.Midas.EstimateDepth(UnityEngine.Texture,System.Boolean)
 
-    void Start() {
-        // Initialize Midas with default parameters
-        midasInstance = new Midas();
+```CSharp
+// Estimate depth from an input texture
+var predictedDepth = midas.EstimateDepth(inputImage);
 
-    }
+// ... use predictedDepth as needed
+```
 
-    void EstimateDepth() {
-        // Estimate depth from input texture
-        midasInstance.EstimateDepth(inputImage);
+Finally, when you're done you should call 'Dispose()' to properly free up native memory resources.
 
-        // Access depth result for further processing or visualization
-        RenderTexture depthResult = midasInstance.Result;
+```CSharp
+midas.Dispose();
+```
 
-        // Use depthResult as needed
+You can reuse the same 'Midas' isntance for multiple inferences. But if you only need it once, you might want to use the 'using' statement, which automatically Dispose() for you:
 
-    }
+```CSharp
+using (Midas midas = new Midas()) {
+    // your code
 }
 ```
 
-## Accessing Depth Results
+A simple example on how to use the library can also be found in the 'Basic Sample' that can be imported via the Package Manager.
 
-The depth estimation results are stored in the Result property of the Midas class. This property is a RenderTexture containing the estimated depth.
 
 ## Choosing a Model Type
 
 Use the ModelType property to set the desired Midas model. Default is midas_v21_small_256.
-Changing the model type automatically disposes of the existing model and initializes the new one.
+
+```CSharp
+var midas = new Midas(ModelType.dpt_beit_large_384);
+```
+
+Changing the model type on an existing 'Midas' instance automatically disposes of the existing model and initializes the new one.
+
+```CSharp
+midas.ModelType = ModelType.midas_v21_small_256;
+```
+
 
 ## Choosing a Backend
 
 Use the Backend property to set the desired backend for model execution (GPUCompute by default).
 Changing the backend automatically disposes of the existing model and initializes the new one.
 
-## Normalizing Depth (Optional)
+```CSharp
+midas.Backend = BackendType.CPU;
+```
+
 
-Set the NormalizeDepth property to true if you want to normalize the estimated depth values between 0 and 1. This is mainly useful for visualization.
+## Normalizing Depth
 
-A simple example on how to use the library can be found in the 'Basic Sample' that can be imported via the Package Manager.
+Set the NormalizeDepth property to true if you want to normalize the estimated depth values between 0 and 1. This is mainly useful for visualization.

docs/manual/models.md

@@ -1,39 +1,34 @@
 # MiDaS Models
 
-There are variety of different MiDaS models available. To be able to use them with Unity Sentis, the official models were converted to ONNX using [this colab notebook][colab]. You'll find links to the pretraine models in ONNX format below.
+There are variety of different MiDaS models available. To be able to use them with Unity Sentis, the official models were converted to ONNX using [this colab notebook][colab]. You'll find links to the pretrained models in ONNX format below.
 
 
 ## Overview
 
-| Model Type                    | Size     | Version   |
-|-------------------------------|----------|-----------|
-| [midas_v21_small_256][1]      | 63 MB    | 2.1       |
-| [midas_v21_384][2]            | 397 MB   | 2.1       |
-| [dpt_beit_large_512][3]       | 1.34 GB  | 3.1       |
-| [dpt_beit_large_384][4]       | 1.34 GB  | 3.1       |
-| [dpt_beit_base_384][5]        | 450 MB   | 3.1       |
-| [dpt_swin2_large_384][6]      | 832 MB   | 3.1       |
-| [dpt_swin2_base_384][7]       | 410 MB   | 3.1       |
-| [dpt_swin2_tiny_256][8]       | 157 MB   | 3.1       |
-| [dpt_swin_large_384][9]       | 854 MB   | 3.1       |
-| [dpt_next_vit_large_384][10]  | 267 MB   | 3.1       |
-| [dpt_levit_224][11]           | 136 MB   | 3.0       |
-| [dpt_large_384][12]           | 1.27 GB  | 3.0       |
+| Model Type                    | Size     | MiDaS Version   |
+|-------------------------------|----------|-----------------|
+| [midas_v21_small_256][1]      | 63 MB    | 2.1             |
+| [midas_v21_384][2]            | 397 MB   | 2.1             |
+| [dpt_beit_large_512][3]       | 1.34 GB  | 3.1             |
+| [dpt_beit_large_384][4]       | 1.34 GB  | 3.1             |
+| [dpt_beit_base_384][5]        | 450 MB   | 3.1             |
+| [dpt_swin2_large_384][6]      | 832 MB   | 3.1             |
+| [dpt_swin2_base_384][7]       | 410 MB   | 3.1             |
+| [dpt_swin2_tiny_256][8]       | 157 MB   | 3.1             |
+| [dpt_swin_large_384][9]       | 854 MB   | 3.1             |
+| [dpt_next_vit_large_384][10]  | 267 MB   | 3.1             |
+| [dpt_levit_224][11]           | 136 MB   | 3.0             |
+| [dpt_large_384][12]           | 1.27 GB  | 3.0             |
 
 
 ## Usage
 
-To keep the package size reasonable, only the midas_v21_small_256 model is included with the package when downloading from the Asset Store. To use other models they have to be downloaded to your development system first.
+To keep the package size reasonable, only the @Midas.ModelType.midas_v21_small_256 model is included with the package when downloading from the Asset Store. To use other models you have to downloaded them first.
 
-When you create an instance of the [`Midas`](~/api/Midas.Midas.yml) class you can pass the [`ModelType`](~/api/Midas.ModelType.yml) in the constructor to choose which model to use. In the Unity Editor if you're about to use a model that is not yet present, it will automatically be downloading if you wish to do so.
+When you create an instance of the [`Midas`](~/api/Midas.Midas.yml) class you can pass the [`ModelType`](~/api/Midas.ModelType.yml) in the constructor to choose which model to use. In the Unity Editor if you're about to use a model that is not yet present, it can automatically be downloading if you wish to do so.
 
 Otherwise you can always manually download the ONNX models from the links above and place them inside the Resources/ONNX folder.
 
-    Choose the appropriate model type based on your requirements, considering factors such as model size, architecture, and performance.
-    Utilize the provided methods in the ModelExtensions class to obtain download links, file names, and resource paths for the selected model.
-
-For more information on each model type, refer to the script comments in the ModelType enum and the ModelExtensions class.
-
 
 ## Which Model To Use