diff --git a/README.md b/README.md
index 59b4e34..eb9f69f 100644
--- a/README.md
+++ b/README.md
@@ -110,10 +110,10 @@ If you encounter any issues or performance problems, refer to the [TROUBLESHOOTI
 
 ### Ubuntu 
 
-Follow the instructions reported [here](./docs/PYTHON-VIRTUAL-ENVS.md) for creating a new virtual environment `pyslam` with **venv**.  The procedure has been tested on *Ubuntu 18.04*, *20.04*, *22.04* and *24.04*. 
-
-If you prefer **conda**, run the scripts described in this other [file](./docs/CONDA.md).
+- With **venv**: Follow the instructions reported [here](./docs/PYTHON-VIRTUAL-ENVS.md).  The procedure has been tested on *Ubuntu 18.04*, *20.04*, *22.04* and *24.04*. 
+- With **conda**: Run the procedure described in this other [file](./docs/CONDA.md).
 
+Both procedures will create a new virtual environment `pyslam`.
 
 ### MacOS
 
diff --git a/install_pip3_packages.sh b/install_pip3_packages.sh
index e863f2f..0b07c8f 100755
--- a/install_pip3_packages.sh
+++ b/install_pip3_packages.sh
@@ -88,7 +88,8 @@ else
     install_pip_package torchvision==0.17               
 fi 
 
-install_pip_package rerun-sdk #==0.17.0
+pip install "rerun-sdk>=0.17.0"
+
 install_pip_package ujson
 install_pip_package tensorflow_hub  # required for VPR
 
diff --git a/viz/rerun_interface.py b/viz/rerun_interface.py
index 9bce9bf..f20e2b6 100644
--- a/viz/rerun_interface.py
+++ b/viz/rerun_interface.py
@@ -1,7 +1,7 @@
 import numpy as np
 import cv2
 import rerun as rr              # pip install rerun-sdk
-import rerun.blueprint as rrb
+
 import utils_geom as utils_geom
 import math as math
 from camera import Camera
@@ -72,6 +72,7 @@ def init3d(img_compress=False) -> None:
     
     @staticmethod
     def init_vo(img_compress=False) -> None:
+        import rerun.blueprint as rrb
         # Setup the blueprint
         Rerun.blueprint = rrb.Vertical(
             rrb.Horizontal(