pixel-perfect-sfm
pixel-perfect-sfm copied to clipboard
cvg
Pixel-Perfect Structure-from-Motion with Featuremetric Refinement (ICCV 2021, Best Student Paper Award)
when running below code, error occurs `sfm = PixSfM({"dense_features": {"max_edge": 1024}}) refined, sfm_outputs = sfm.reconstruction(ref_dir, images, sfm_pairs, features, matches, image_list=references)`  but the type of 'reconstruction' is `pycolmap.reconstruction`, how to...
when refiner = PixSfM(), super(_open_file, self).__init__(open(name, mode)) FileNotFoundError: [Errno 2] No such file or directory: '/home/ai/workspace/pixel-perfect-sfm/pixsfm/features/models/checkpoints/s2dnet_weights.pth'
Dear authors, Really appreciate your efforts to open source this great paper. When I was testing my data, sometimes it can't run through the costmaps generation process. I am using...
I run it on ubnutu18, cuda11.2 but when i preceed : " # run pixsfm sfm = PixSfM({"dense_features": {"max_edge": 1024}}) refined, sfm_outputs = sfm.reconstruction(ref_dir, images, sfm_pairs, features, matches, image_list=references) #...
hi, ''dict: Return dict of featuremaps. For format see features/README.md'',but I can not find features/README.md
- Allow extracting costmaps from dense features - Store features to H5 in dense if it requires less memory (e.g. for semi-dense local features)
Releases GPU resources before/after dense feature extraction (by moving the model to CPU).
Add support for [kornia's DenseSIFTDescriptor](https://kornia.readthedocs.io/en/latest/_modules/kornia/feature/siftdesc.html#DenseSIFTDescriptor) as dense features. Requires kornia>=0.6.4.
Updates the config of the sift extractor in the ETH3D benchmark to be compatible with the latest API changes in hloc.
Hi, Paul@Skydes, I've met some issues during bundle adjustment .  It seems that no bundle adjustment process is done and the cost didn't change at all. So, how could...
