Your dataset structure follows common LLFF, and I understand that the main issue with custom datasets and LLFF is the lack of file names being presented to the model. I had similar issues with nvdiffrec and a simple list solves any number of memory leaks that happen when loading images/files rejected by colmap.
a "view_imgs.txt" is pretty important I'd think, and I'm glad some of the example datasets use a poses.npy -I do not understand the reasoning to use remove.bg masks, construct datasets with another .db file, and pickle a list of files (instead of a readable .txt) that users might want to edit when making their own sets.
https://github.com/snap-research/NeROIC/blob/e535d50077ab57c2f39ae55543c8543793857676/dataset/llff.py#L243 when I am trying to handle masks, in their own separate folder, would I want them just to be a b/w image out of any number of salient object matting repos, or images specifically from remove.bg of a separate size (to then use bicubic filtering on), only in the alpha, and containing an entire unused image?
There are 0 technological limitations on making a dataset renderable and testable in instant-ngp, meshable in nvdiffrec (and this repo), optimizable in AdaNeRF and R2L, and still be created from a video shot on a phone. If you're planning on making a dataset creation guide, please dont use removebg filenames, dont use new db files, dont use non user-readable lists of files (it takes one extra line to parse a .txt file), and have support for traditional b/w masks.
all that's needed is /images, /masks, imgs.txt, and a poses.npy (pts seems like it's to build a bounding box and isn't in all your example sets)
lowering that barrier allows anyone who knows how to run a script to make datasets, and it's WHY instant-ngp worked, anyone could try it out with ffmpeg and a script. Forks are being made to test datasets made from my colmap2poses script, if a simple colmap2NeROIC script is needed to read colmap data I can make a push with a more forgiving LLFF dataloader and said script.
Your dataset structure follows common LLFF, and I understand that the main issue with custom datasets and LLFF is the lack of file names being presented to the model. I had similar issues with nvdiffrec and a simple list solves any number of memory leaks that happen when loading images/files rejected by colmap.
a "view_imgs.txt" is pretty important I'd think, and I'm glad some of the example datasets use a poses.npy -I do not understand the reasoning to use remove.bg masks, construct datasets with another .db file, and pickle a list of files (instead of a readable .txt) that users might want to edit when making their own sets. https://github.com/snap-research/NeROIC/blob/e535d50077ab57c2f39ae55543c8543793857676/dataset/llff.py#L243 when I am trying to handle masks, in their own separate folder, would I want them just to be a b/w image out of any number of salient object matting repos, or images specifically from remove.bg of a separate size (to then use bicubic filtering on), only in the alpha, and containing an entire unused image?
There are 0 technological limitations on making a dataset renderable and testable in instant-ngp, meshable in nvdiffrec (and this repo), optimizable in AdaNeRF and R2L, and still be created from a video shot on a phone. If you're planning on making a dataset creation guide, please dont use removebg filenames, dont use new db files, dont use non user-readable lists of files (it takes one extra line to parse a .txt file), and have support for traditional b/w masks. all that's needed is /images, /masks, imgs.txt, and a poses.npy (pts seems like it's to build a bounding box and isn't in all your example sets) lowering that barrier allows anyone who knows how to run a script to make datasets, and it's WHY instant-ngp worked, anyone could try it out with ffmpeg and a script. Forks are being made to test datasets made from my colmap2poses script, if a simple colmap2NeROIC script is needed to read colmap data I can make a push with a more forgiving LLFF dataloader and said script.