0.6.0-preview.1

Added

• All-new editor interface for the Labeling component and Label Configuration assets. The new UI improves upon various parts of the label specification and configuration workflow, making it more efficient and less error-prone to setup a new Perception project.

• Added support for labeling Terrain objects. Trees and details are not labeled but will occlude other objects.

• Added instance segmentation labeler.

• Added support for full screen visual overlays and overlay manager.

• Added Assets->Perception menu for current and future asset preparation and validation tools. Currently contains one function which lets the user create prefabs out of multiple selected models with one click, removing the need for going through all models individually.

Changed

• Updated dependencies to com.unity.simulation.capture:0.0.10-preview.14, com.unity.simulation.core:0.0.10-preview.20, and com.unity.burst:1.3.9.

• Changed InstanceSegmentationImageReadback event to provide a NativeArray<Color32> instead of NativeArray<uint>.

• Expanded all Unity Simulation references from USim to Unity Simulation.

• Uniform and Normal samplers now serialize their random seeds.

• The ScenarioBase's GenerateIterativeRandomSeed() method has been renamed to GenerateRandomSeedFromIndex().

Fixed

• UnitySimulationScenario now correctly deserializes app-params before offsetting the current scenario iteration when executing on Unity Simulation.

• Fixed Unity Simulation nodes generating one extra empty image before generating their share of the randomization scenario iterations.

• Fixed enumeration in the CategoricalParameter.categories property.

• The GenerateRandomSeedFromIndex method now correctly hashes the current scenario iteration into the random seed it generates.

• Corrupted .meta files have been rebuilt and replaced.

• The Randomizer list inspector UI now updates appropriately when a user clicks undo.

0.5.0-preview.1

To install, follow the installation instructions or the Perception tutorial.

Known Issues

Creating a new 2020.1.x project and adding the perception package to the project causes a memory error that is a known issue in 2020.1 editors. Users can remedy this issue by closing and reopening the editor.

Added

• Randomization tools were redesigned. With this release we introduce the new Randomizers and RandomizerTags. These tools gather all your randomizations in one place, making it easier to control the order of operations and switch between different randomization strategies quickly. This will enable you to iterate and experiment more efficiently, and reuse your randomization scenarios in different Unity projects. In addition, the tools are now more flexible and can be easily extended or customized for specific use-cases through code.

• You can now easily run your projects on Unity Simulation using the new “Run in USim” window, which lets you choose the number of iterations in your Randomization scenario, as well as the number of simulation nodes the job will be distributed on.

• Added support for generating 3D bounding box ground truth data

Follow the new Perception tutorial for instructions on how to utilize the new Randomization tools and "Run in USim" window.

Removed

Removed ParameterConfigurations (replaced with Randomizers)

Fixed

Fixed visualization issue where object count and pixel count labelers were shown stale values
Fixed visualization issue where HUD entry labels could be too long and take up the entire panel

0.4.0-preview.1

To install, follow the getting started guide.

Added

Added new experimental randomization tools

Added support for 2020.1

Added Labeling.RefreshLabeling(), which can be used to update ground truth generators after the list of labels or the renderers is changed

Added support for renderers with MaterialPropertyBlocks assigned to individual materials

Changed

Changed the way realtime visualizers rendered to avoid rendering conflicts

Changed default labeler ids to be lower-case to be consistent with the ids in the dataset

Switched to latest versions of com.unity.simulation.core and com.unity.simulation.capture

Fixed

Fixed 2d bounding boxes being reported for objects that do not match the label config.

Fixed a categorical parameter UI error in which deleting an individual option would successfully remove the option from the UI but only serialize the option to null during serialization instead of removing it

Fixed the "Application Frequency" parameter UI field not initializing to a default value

Fixed the IterateSeed() method where certain combinations of indices and random seeds would produce a random state value of zero, causing Unity.Mathematics.Random to throw an exception

Fixed labeler editor to allow for editing multiple labelers at a time

Fixed labeler editor to ensure that when duplicating prefabs all labeler entries are also duplicated

Fixed colors in semantic segmentation images being darker than those specified in the label config

Fixed objects being incorrectly labeled when they do not match any entries in the label config

Fixed lens distortion in URP and HDRP now being applied to ground truth

0.3.0-preview.2

To install, follow the getting started guide.

Added

Added realtime visualization capability to the perception package.
Added visualizers for built-in labelers: Semantic Segmentation, 2D Bounding Boxes, Object Count, and Rendered Object Info.
Added references to example projects in manual.
Added notification when an HDRP project is in Deferred Only mode, which is not supported by the labelers.

Changed

Updated to com.unity.simulation.capture version 0.0.10-preview.10 and com.unity.simulation.core version 0.0.10-preview.17
Changed default labeler IDs to be lower-case to be consistent with the dataset.

Fixed

Fixed errors in example script when exiting play mode
Fixed colors in semantic segmentation output not matching config

0.2.0-preview.2

To install, follow the getting started guide.

Fixed

Fixed bug that prevented RGB captures to be written out to disk
Fixed compatibility with [email protected]

0.2.0.preview.1

To install, follow the getting started guide.

Added

Added CameraLabeler, an extensible base type for all forms of dataset output from a camera.
Added LabelConfig<T>, a base class for mapping labels to data used by a labeler. There are two new derived types - ID label config and semantic segmentation label config.

Changed

Moved the various forms of ground truth from PerceptionCamera into various subclasses of CameraLabeler.
Renamed SimulationManager to DatasetCapture.
Changed Semantic Segmentation to take a SemanticSegmentationLabelConfig, which maps labels to color pixel values.