Add Support for Meshroom data convertion

[parodiniccolo]

Added Support for Meshroom in ns-process-data

Added support to convert Meshroom custom data with ns-process-data. Based on mr2nerf

usage: ns-process-data meshroom [-h] [MESHROOM OPTIONS]

Process Meshroom data into a nerfstudio dataset. This script assumes that cameras have been aligned using Meshroom. After alignment, it is necessary to export the camera poses as a .json file.

Optional: Meshroom does not align or constrain solved cameras. You may want to add a SfMTransform after the StructureFromMotion node, set the Transformation Method to Manual, and adjust camera positioning.

When you start Meshroom processing, it generates an output folder for the ConvertSfMFormat node (right click > Open Folder). The sfm.json file needed for this script's --input function will be generated there.

Features

This script:

1. Scales images to a specified size
2. Converts Meshroom poses into the nerfstudio format

Options

Option	Description
-h, --help	Show this help message and exit
--json PATH	Path to the Meshroom sfm.json file (required)
--data PATH	Path to the data, either a video file or a directory of images (required)
--output-dir PATH	Path to the output directory (required)
--eval-data {None}|PATH	Path to the eval data, either a video file or a directory of images. If set to None, the data will be used both for training and eval (default: None)
--verbose, --no-verbose	If True, print extra logging (default: False)
--ply {None}|PATH	Path to the Meshroom point export ply file (default: None)
--num-downscales INT	Number of times to downscale the images. Downscales by 2 each time. For example, a value of 3 will downscale the images by 2x, 4x, and 8x (default: 3)
--max-dataset-size INT	Max number of images to train on. If the dataset has more, images will be sampled approximately evenly. If -1, use all images (default: 600)