Sazoji
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| // ==UserScript== | |
| // @name twitter to nitter | |
| // @match *://twitter.com/* | |
| // @run-at document-start | |
| // @author Sazoji | |
| // @description Redirects from twitter to nitter | |
| // @grant none | |
| // @version 0.0.1 | |
| // ==/UserScript== |
Sazoji
/ colmap2poses.py
Last active
December 18, 2023 05:08
colmap2poses is simple! make sure you have opencv (and rembg if you wish to mask). The only thing required is a path to the dataset folder, containing a "images" subfolder. Avoid weird filenames.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # most of the code is refactored colmap parsing from LLFF, a GPLv3 project. | |
| # this is meant to be comparable to instant-ngp's colmap2nerf.py, and uses the | |
| # same arguments, with additional functions for masking and LLFF format poses. | |
| # LLFF format .npy files will always be made, remove if you ONLY want NeRF format | |
| #~~~provide a dataset folder path with another "image" subfolder with the pics~~~ | |
| # ~~~colmap can be installed to PATH or linked as an argument (--colmap_path)~~~ | |
| # usage: (for LLFF format, nvdiffrec) | |
| # colmap2poses.py --mask "/path/to/dataset/" |