Add links to DiffVox

README.md

@@ -126,9 +126,12 @@ This work includes a lot of real-world usecases of `DiffDRR` including
 ### Volume Reconstruction
 
 `DiffDRR` is differentiable with respect to the 3D volume as well as camera poses.
-Therefore, it could (in theory) be used for volume reconstruction via differentiable
-rendering. However, this feature has not been robustly tested and is currently 
-under active development (see [`reconstruction.ipynb`](https://vivekg.dev/DiffDRR/tutorials/reconstruction.html))!
+Therefore, it can be used for volume reconstruction via differentiable
+rendering (see [`reconstruction.ipynb`](https://vivekg.dev/DiffDRR/tutorials/reconstruction.html))!
+
+#### *🆕 Examples on Real-World Data 🆕*
+
+For an in-depth example using `DiffDRR` for cone-beam CT reconstruction, check out [`DiffVox`](https://github.com/hossein-momeni/DiffVox).
 
 ## Development
 
@@ -193,3 +196,12 @@ If the 2D/3D registration capabilities are helpful, please cite our followup, [`
       pages={11662--11672},
       year={2024}
     }
+
+If you use the 3D CBCT reconstruction capabilities, please cite our followup, [`DiffVox`](https://arxiv.org/abs/2312.06358):
+
+    @article{momeni2024voxel,
+      title={Voxel-based Differentiable X-ray Rendering Improves Self-Supervised 3D CBCT Reconstruction},
+      author={Momeni, Mohammadhossein and Gopalakrishnan, Vivek and Dey, Neel and Golland, Polina and Frisken, Sarah},
+      booktitle={Machine Learning and the Physical Sciences, NeurIPS 2024},
+      year={2024}
+    }

notebooks/index.ipynb

@@ -195,9 +195,12 @@
     "### Volume Reconstruction\n",
     "\n",
     "`DiffDRR` is differentiable with respect to the 3D volume as well as camera poses.\n",
-    "Therefore, it could (in theory) be used for volume reconstruction via differentiable\n",
-    "rendering. However, this feature has not been robustly tested and is currently \n",
-    "under active development (see [`reconstruction.ipynb`](https://vivekg.dev/DiffDRR/tutorials/reconstruction.html))!"
+    "Therefore, it can be used for volume reconstruction via differentiable\n",
+    "rendering (see [`reconstruction.ipynb`](https://vivekg.dev/DiffDRR/tutorials/reconstruction.html))!\n",
+    "\n",
+    "#### *🆕 Examples on Real-World Data 🆕*\n",
+    "\n",
+    "For an in-depth example using `DiffDRR` for cone-beam CT reconstruction, check out [`DiffVox`](https://github.com/hossein-momeni/DiffVox)."
    ]
   },
   {

notebooks/tutorials/reconstruction.ipynb

@@ -24,7 +24,9 @@
     "2. Initialize a moving DRR module with a random 3D volume\n",
     "3. Measure the loss between the target X-ray and projections from the moving volume\n",
     "4. Backpropogate this loss to the volume of the moving DRR and render from the new volume\n",
-    "5. Repeat Steps 3-4 until the loss has converged"
+    "5. Repeat Steps 3-4 until the loss has converged\n",
+    "\n",
+    "For an in-depth example using `DiffDRR` for cone-beam CT reconstruction, check out our latest work, [`DiffVox`](https://github.com/hossein-momeni/DiffVox)."
    ]
   },
   {