Readme: more user facing

README.md

@@ -1,14 +1,83 @@
 # Lightly Studio Plugins
 
-A collection of plugins for [Lightly Studio](https://github.com/lightly-ai/lightly-studio). Each plugin is independently pip-installable and auto-discovered via Python entry points.
+A collection of installable plugins that extend the base functionality of [Lightly Studio](https://github.com/lightly-ai/lightly-studio).
 
-| Plugin | Description | Maintainer | Install |
-|---|---|---|---|
-| [BBox auto propagation nano tracker](plugins/bbox_auto_propagation_nano_tracker/)|Auto bbox propagation using nano tracker|Lightly| `pip install git+https://github.com/lightly-ai/lightly-studio-plugins.git#subdirectory=plugins/bbox_auto_propagation_nano_tracker/`|
-| [SAM3 Segmentation](plugins/sam3_segmentation/)|Automatic instance segmentation using SAM3 with a text prompt. Requires HuggingFace access to `facebook/sam3`.|Lightly| `pip install git+https://github.com/lightly-ai/lightly-studio-plugins.git#subdirectory=plugins/sam3_segmentation/`|
-| [LightlyTrain object detection inference](plugins/lightly_train_object_detection_inference/)|LightlyTrain inference operator for object detection auto-labeling|Lightly| `pip install git+https://github.com/lightly-ai/lightly-studio-plugins.git#subdirectory=plugins/lightly_train_object_detection_inference/`|
+Each plugin in this repository is packaged independently, installs in a single command, and is auto-discovered by Lightly Studio via Python entry points.
 
-## Adding a New Plugin
+![SAM3 Segmentation Plugin](plugins/sam3_segmentation/sam3_plugin.gif)
+
+<p align="center"><em>SAM3 Segmentation Plugin</em></p>
+
+Each plugin entry below includes the exact copy-paste install command. After installation, the plugin is available in Lightly Studio automatically.
+
+## Available Plugins
+
+- [BBox auto propagation nano tracker](plugins/bbox_auto_propagation_nano_tracker/)  
+  Propagates boxes from one annotated video frame to other frames in the same video.
+
+  <details>
+  <summary>Details</summary>
+
+  If triggered from a frame, all bounding box annotations on that frame are
+  propagated. If triggered from an annotation, only the selected annotation is
+  propagated.
+
+  - Scope: video only, within a single video
+  - Entry points: frame or annotation
+  - Controls: forward and backward propagation windows in seconds
+  - Tradeoff: uses OpenCV NanoTracker, which is lightweight and fast on many
+    machines but less robust on difficult motion, occlusion, or scale changes
+  - Maintainer: Lightly
+  - Install:
+    `pip install git+https://github.com/lightly-ai/lightly-studio-plugins.git#subdirectory=plugins/bbox_auto_propagation_nano_tracker/`
+
+  </details>
+
+- [SAM3 Segmentation](plugins/sam3_segmentation/)  
+  Segments all instances matching a text prompt in a single image or across the current view.
+
+  <details>
+  <summary>Details</summary>
+
+  This is designed for dataset-wide prompt-based labeling workflows with
+  class-like prompts such as `person`, `car`, or `dog`.
+
+  - Scope: single image or images in the current view
+  - Input: text prompt
+  - Output: segmentation masks
+  - Labels: the prompt text is used as the annotation class name
+  - Requirement: Hugging Face access to `facebook/sam3`
+  - Maintainer: Lightly
+  - Install:
+    `pip install git+https://github.com/lightly-ai/lightly-studio-plugins.git#subdirectory=plugins/sam3_segmentation/`
+
+  </details>
+
+- [LightlyTrain object detection inference](plugins/lightly_train_object_detection_inference/)  
+  Runs LightlyTrain object detection inference on one image or the current view for auto-labeling.
+
+  <details>
+  <summary>Details</summary>
+
+  You can use built-in LightlyTrain models for quick bootstrapping or provide a
+  path to your own LightlyTrain checkpoint.
+
+  - Scope: single image or images in the current view
+  - Input: LightlyTrain model name or local path to a LightlyTrain checkpoint
+  - Output: object detection annotations
+  - Labels: class labels are read from the loaded model and created in the
+    dataset if they do not exist yet
+  - Recommended models:
+    `dinov3/convnext-large-ltdetr-coco` for best performance,
+    `dinov3/vits16-ltdetr-coco` for a speed/quality balance,
+    `picodet-l-coco` for resource-constrained environments
+  - Maintainer: Lightly
+  - Install:
+    `pip install git+https://github.com/lightly-ai/lightly-studio-plugins.git#subdirectory=plugins/lightly_train_object_detection_inference/`
+
+  </details>
+
+## Contributing Plugins
 
 1. Create a new directory under `plugins/`:
    ```

plugins.toml

@@ -1,23 +1,23 @@
 [[plugins]]
 id = "lightly_plugins_bbox_auto_propagation_nano_tracker"
 name = "BBox auto propagation nano tracker"
-description = "Auto bbox propagation using nano tracker"
+description = "Propagates bounding boxes across frames in the same video using OpenCV NanoTracker"
 source = "local:plugins/bbox_auto_propagation_nano_tracker"
 maintainer = "lightly"
 tags = ["auto-labeling", "tracking"]
 
 [[plugins]]
 id = "lightly_plugins_sam3_segmentation"
 name = "SAM3 Segmentation"
-description = "Automatic instance segmentation using SAM3 with a text prompt"
+description = "Segments all instances matching a text prompt in a single image or the current image view"
 source = "local:plugins/sam3_segmentation"
 maintainer = "lightly"
 tags = ["auto-labeling", "segmentation"]
 
 [[plugins]]
 id = "lightly_plugins_lightly_train_object_detection_inference"
 name = "LightlyTrain object detection inference"
-description = "LightlyTrain inference operator for object detection auto-labeling"
+description = "Runs LightlyTrain object detection inference on a single image or the current filtered image view"
 source = "local:plugins/lightly_train_object_detection_inference"
 maintainer = "lightly"
 tags = ["auto-labeling", "object-detection", "inference"]