Open chungmin99 opened 1 year ago
i suggest to move KMeans and torch.pca_low_rank to the _get_outputs_for_camera_raybundle function (aggregate all get_outputs from one image there and after perform dim reduction) to prevent different color palitre on a one image
@chungmin99 , were you able to fully integrate Dinov2 with LERF?
Added capability to use DINOv2 models
(Using implementation/torchhub as described by https://github.com/facebookresearch/dinov2)
TODOs: