Uses new replicator API for tiled rendering (#110)

# Description

This change switches to the newly added replicator API for tiled
rendering. All tiled rendering behaviors are the same as before. The API
provides a cleaner interface to initialize tiled rendering.

## Type of change
- New feature (non-breaking change which adds functionality)

## Checklist

- [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with
`./isaaclab.sh --format`
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [x] I have updated the changelog and the corresponding version in the
extension's `config/extension.toml` file
- [ ] I have added my name to the `CONTRIBUTORS.md` or my name already
exists there

<!--
As you go through the checklist above, you can mark something as done by
putting an x character in it

For example,
- [x] I have done this task
- [ ] I have not done this task
-->

docs/source/features/tiled_rendering.rst

@@ -11,7 +11,8 @@ Tiled Rendering
 
     This feature is only available from Isaac Sim version 4.2.0 onwards.
 
-    Tiled rendering in combination with image processing networks require heavy memory resources, especially at larger resolutions. We recommend running at 256 cameras in the scene on RTX 4090 GPUs or similar.
+    Tiled rendering in combination with image processing networks require heavy memory resources, especially at larger resolutions. We recommend running at 512 cameras in the scene on RTX 4090 GPUs or similar.
+
 
 Tiled rendering APIs provide a vectorized interface for collecting data from camera sensors.
 This is useful for reinforcement learning environments requiring vision in the loop.
@@ -59,6 +60,21 @@ environment. For example:
     python source/standalone/workflows/rl_games/train.py --task=Isaac-Cartpole-RGB-Camera-Direct-v0 --headless --enable_cameras
 
 
+.. warning::
+
+    There are currently a few limitations with tiled rendering:
+
+    * Number of cameras must be a perfect square
+    * Tile resolution must be a square
+    * Due to upsampling in the denoising process, image quality may appear different when running with different numbers of cameras.
+      To overcome this issue, we can use the DLAA denoiser at the cost of some performance.
+
+      .. code-block:: python
+
+        import omni.replicator.core as rep
+        rep.settings.set_render_rtx_realtime(antialiasing="DLAA")
+
+
 Annotators and Data Types
 ^^^^^^^^^^^^^^^^^^^^^^^^^
 

source/apps/isaaclab.python.headless.rendering.kit

@@ -56,10 +56,6 @@ exts."omni.renderer.core".present.enabled=false
 # Disabling these settings reduces renderer VRAM usage and improves rendering performance, but at some quality cost
 rtx.raytracing.cached.enabled = false
 rtx.ambientOcclusion.enabled = false
-rtx-transient.dlssg.enabled = false
-
-rtx.sceneDb.ambientLightIntensity = 1.0
-rtx.directLighting.sampledLighting.enabled = true
 
 # Avoids unnecessary GPU context initialization
 renderer.multiGpu.maxGpuCount=1

source/apps/isaaclab.python.rendering.kit

@@ -56,10 +56,6 @@ exts."omni.renderer.core".present.enabled=false
 # Disabling these settings reduces renderer VRAM usage and improves rendering performance, but at some quality cost
 rtx.raytracing.cached.enabled = false
 rtx.ambientOcclusion.enabled = false
-rtx-transient.dlssg.enabled = false
-
-rtx.sceneDb.ambientLightIntensity = 1.0
-rtx.directLighting.sampledLighting.enabled = true
 
 # Avoids unnecessary GPU context initialization
 renderer.multiGpu.maxGpuCount=1

source/extensions/omni.isaac.lab/omni/isaac/lab/sensors/camera/tiled_camera.py

@@ -12,12 +12,11 @@ from collections.abc import Sequence
 from tensordict import TensorDict
 from typing import TYPE_CHECKING, Any
 
-import carb
 import omni.usd
 import warp as wp
 from omni.isaac.core.prims import XFormPrimView
 from omni.isaac.version import get_version
-from pxr import Usd, UsdGeom
+from pxr import UsdGeom
 
 from omni.isaac.lab.utils.warp.kernels import reshape_tiled_image
 
@@ -184,22 +183,10 @@ class TiledCamera(Camera):
             sensor_prim = UsdGeom.Camera(cam_prim)
             self._sensor_prims.append(sensor_prim)
 
-        # get full resolution for all tiles
-        full_resolution = self._tiled_image_shape()
-
-        # Set carb settings for tiled rendering
-        carb_settings = carb.settings.get_settings()
-        carb_settings.set("/rtx/viewTile/height", self.cfg.height)
-        carb_settings.set("/rtx/viewTile/width", self.cfg.width)
-        carb_settings.set("/rtx/viewTile/count", self._view.count)
-
-        # Create render product
-        rp = rep.create.render_product(self._view.prim_paths[0], full_resolution)
-
-        # Attach all cameras to render product
-        rp_prim = stage.GetPrimAtPath(rp.path)
-        with Usd.EditContext(stage, stage.GetSessionLayer()):
-            rp_prim.GetRelationship("camera").SetTargets(self._view.prim_paths)
+        # Create replicator tiled render product
+        rp = rep.create.render_product_tiled(
+            cameras=self._view.prim_paths, tile_resolution=(self.cfg.width, self.cfg.height)
+        )
         self._render_product_paths = [rp.path]
 
         # Define the annotators based on requested data types