Losses - nerfstudio
Scale gradients by the ray distance to the pixel as suggested in Radiance Field Gradient Scaling for Unbiased Near-Camera Training paper Note: The scaling is applied on the interval of [0, 1] …
Models - nerfstudio
Use gradient scaler where the gradients are lower for points closer to the camera. class nerfstudio.models.instant_ngp.NGPModel(config: InstantNGPModelConfig, **kwargs)[source] #
nerfstudio.model_components.losses - nerfstudio
[docs] class GradientLoss(nn.Module): """ multiscale, scale-invariant gradient matching term to the disparity space.
Engine - nerfstudio
Number of steps between randomly sampled batches of rays. steps_per_eval_image: int = 500 # Number of steps between single eval images. steps_per_save: int = 1000 # Number of steps …
API - nerfstudio
GradientLoss.gradient_loss() MiDaSMSELoss MiDaSMSELoss.forward() ScaleAndShiftInvariantLoss ScaleAndShiftInvariantLoss.forward() …
Model components - nerfstudio
GradientLoss.gradient_loss() MiDaSMSELoss MiDaSMSELoss.forward() ScaleAndShiftInvariantLoss ScaleAndShiftInvariantLoss.forward() …
Feature Splatting - nerfstudio
Paper Website Code Feature Splatting distills SAM-enhanced CLIP features into 3DGS for segmentation and editing Installation: First install nerfstudio dependencies. Then run: Running …
Instruct-GS2GS - nerfstudio
Paper Website Code Instruct-GS2GS enables instruction-based editing of 3D Gaussian Splatting scenes via a 2D diffusion model Installation: First install nerfstudio dependencies. Then run: …
nerfstudio.models.vanilla_nerf - nerfstudio
[docs] def get_outputs(self, ray_bundle: RayBundle): if self.field_coarse is None or self.field_fine is None: raise ValueError("populate_fields() must be called before get_outputs") # uniform …
Renderers - nerfstudio
Collection of renderers Example: