add multi-physics models to user guide

Andrewwango · Andrewwango · commit fdab7cee1a7b · 2025-08-01T22:49:14.000+01:00
diff --git a/docs/source/user_guide/reconstruction/artifact.rst b/docs/source/user_guide/reconstruction/artifact.rst
@@ -16,9 +16,13 @@ reconstruction network :class:`deepinv.models.Reconstructor` :math:`R` by doing
   | This option serves as a wrapper to obtain a :class:`Reconstructor <deepinv.models.Reconstructor>`, and can be used to adapt a generic denoiser or image-to-image network into one that is specific to an inverse problem.
 
 
+.. _general_reconstructors:
+
 General reconstruction models
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-We provide the following list of multiphysics reconstruction models.
+We provide the following list of reconstruction models trained on multiple various physics and datasets
+to provide robustness to different problems.
+
 See :ref:`pretrained-weights` for more information on pretrained denoisers.
 
 .. list-table:: Multiphysics reconstruction models
diff --git a/docs/source/user_guide/reconstruction/introduction.rst b/docs/source/user_guide/reconstruction/introduction.rst
@@ -64,13 +64,17 @@ description of their reconstruction performance and speed.
      - No
      - Yes
      - Depends
+   * - :ref:`Multi-physics models <general_reconstructors>`
+     - Models trained on multiple various physics and datasets for robustness to different problems.
+     - No
+     - No
+     - No
    * - :ref:`Specific network architectures <specific>`
      - Off-the-shelf architectures for specific inverse problems.
      - Yes
      - No
      - No
 
-
 .. note::
 
         Some algorithms might be better at reconstructing images with good perceptual quality (e.g. diffusion methods)
