Open pooncs opened 1 year ago
Hi @pooncs, Thanks for your interest! Since we're currently preoccupied with other tasks, I could guide you how to do it if you wish to do so.
Variable-sized images and custom intrinsics can be supported by adding a new type of pytorch dataset, similar to how the MultiviewDataset was created (see: https://github.com/NVIDIAGameWorks/kaolin-wisp/blob/8df9d034224da45053bf135a2e9a640edf23d084/wisp/datasets/multiview_dataset.py#L17):
MultiviewIntrinsicsDataset
class. You can use MultiviewDataset
as a reference.nerf_standard.py
- you want to update this logic (https://github.com/NVIDIAGameWorks/kaolin-wisp/blob/8df9d034224da45053bf135a2e9a640edf23d084/wisp/datasets/formats/nerf_standard.py#L74).
MultiviewIntrinsicsDataset
class, invoke your updated logic and again take care not to break due to stacking images together (the assumption in MultiviewDataset
no longer holds).If you post a MR, I can help quickly review and integrate it (we could also replace the current logic if the performance penalty is negligible).
Hi I am coming from Instant-ngp, and lately, they added the capability to load individual intrinsics (by moving the global intrinsics in the json to each image). This also allows for loading different size images (or rotated images). I was wondering if there is any plans to add this capability? Thanks.