Dummy forward function.

Forward function for testing. Args: inputs (list[Tensor]): List of multi-level img features. img_metas (list[dict]): L

Forward function for training. Args: inputs (list[Tensor]): List of multi-level img features. img_metas (list[dict]):

Copied from Plenoxels Continuous learning rate decay function. Adapted from JaxNeRF The returned rate is lr_init when step=0 and lr_fina

ViT weight initialization, original timm impl (for reproducibility)

ViT weight initialization, original timm impl (for reproducibility)

Scale and translation invariant MSE loss Args: pred_depth: predicted depth [B, 1, H, W] target_depth: ground truth depth [B,

pred_depth shape: [B, V, 1, H, W] target_depth shape: [B, V, 1, H, W] impl according to MiDaS paper Eq.6 and Splatter-a-Video paper Eq.4

The iteration step during training. This method defines an iteration step during training, except for the back propagation and optimi

The iteration step during validation. This method shares the same signature as :func:`train_step`, but used during val epochs. Note t

Close to ViT-giant, with embed-dim 1536 and 24 heads => embed-dim per head 64

Close to ViT-giant, with embed-dim 1536 and 24 heads => embed-dim per head 64