diff --git a/nerfstudio/models/gaussian_splatting.py b/nerfstudio/models/gaussian_splatting.py
index b8102e7368..154224c369 100644
--- a/nerfstudio/models/gaussian_splatting.py
+++ b/nerfstudio/models/gaussian_splatting.py
@@ -32,7 +32,6 @@
 from pytorch_msssim import SSIM
 from torch.nn import Parameter
 
-from nerfstudio.cameras.camera_optimizers import CameraOptimizer, CameraOptimizerConfig
 from nerfstudio.cameras.cameras import Cameras
 from nerfstudio.data.scene_box import OrientedBox
 from nerfstudio.engine.callbacks import TrainingCallback, TrainingCallbackAttributes, TrainingCallbackLocation
@@ -142,8 +141,6 @@ class GaussianSplattingModelConfig(ModelConfig):
     """stop splitting at this step"""
     sh_degree: int = 3
     """maximum degree of spherical harmonics to use"""
-    camera_optimizer: CameraOptimizerConfig = field(default_factory=CameraOptimizerConfig)
-    """camera optimizer config"""
     use_scale_regularization: bool = False
     """If enabled, a scale regularization introduced in PhysGauss (https://xpandora.github.io/PhysGaussian/) is used for reducing huge spikey gaussians."""
     max_gauss_ratio: float = 10.0
@@ -211,10 +208,6 @@ def populate_modules(self):
         self.crop_box: Optional[OrientedBox] = None
         self.back_color = torch.zeros(3)
 
-        self.camera_optimizer: CameraOptimizer = self.config.camera_optimizer.setup(
-            num_cameras=self.num_train_data, device="cpu"
-        )
-
     @property
     def colors(self):
         if self.config.sh_degree > 0:
@@ -569,8 +562,6 @@ def get_param_groups(self) -> Dict[str, List[Parameter]]:
             Mapping of different parameter groups
         """
         gps = self.get_gaussian_param_groups()
-        # add camera optimizer param groups
-        self.camera_optimizer.get_param_groups(gps)
         return gps
 
     def _get_downscale_factor(self):
@@ -593,9 +584,6 @@ def get_outputs(self, camera: Cameras) -> Dict[str, Union[torch.Tensor, List]]:
             print("Called get_outputs with not a camera")
             return {}
         assert camera.shape[0] == 1, "Only one camera at a time"
-        if self.training:
-            # currently relies on the branch vickie/camera-grads
-            self.camera_optimizer.apply_to_camera(camera)
         if self.training:
             background = torch.rand(3, device=self.device)
         else:
@@ -754,7 +742,6 @@ def get_metrics_dict(self, outputs, batch) -> Dict[str, torch.Tensor]:
         predicted_rgb = outputs["rgb"]
         metrics_dict["psnr"] = self.psnr(predicted_rgb, gt_rgb)
 
-        self.camera_optimizer.get_metrics_dict(metrics_dict)
         metrics_dict["gaussian_count"] = self.num_points
         return metrics_dict