-
Notifications
You must be signed in to change notification settings - Fork 628
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
v1.1 #78
Conversation
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
Member
sarlinpe
commented
Jul 17, 2021
- [BREAKING] improved structure of the SfM folders (triangulation and reconstruction), see #76
- Support for image retrieval (NetVLAD, DIR) and more local features (SIFT, R2D2)
- Support for more datasets: Aachen v1.1, Extended CMU Seasons, RobotCar Seasons, 4Seasons, Cambridge Landmarks, 7-Scenes
- Simplified pipeline and API
- Spatial matcher
- Support for arbitrary paths of features and matches
- Support for matching multiple feature files together
https://github.com/naver/deep-image-retrieval/ Co-authored-by: Paul-Edouard Sarlin <paul.edouard.sarlin@gmail.com>
- fix crash when the images are a list of `str` instead of `Path` - skip query images for which no images were retrieved
* Added SIFT features using PyCOLMAP. * Added asserts for input image. * Fix style Co-authored-by: Mihai Dusmanu <mihai.dusmanu@gmail.com> See #69
* Added NetVLAD implementation. * No whitening layer if whiten=False. * Host the weights on the CVG storage * Fix style Co-authored-by: Mihai Dusmanu <mihai.dusmanu@gmail.com> See #68
…gfix in mutual check, safe writing
Co-authored-by: mhumenbe <martin.humenberger@naverlabs.com>
* add r2d2 feature extractor * rename required_data_keys to required_inputs * pass mean and std as list literal to the tvf.Normalize function and store the tvf.Normalize function norm_rgb as a member function in the class. The device will be take care in tvf.functional.Normalize * rename conf keys and resolve error&warnings based on flake8 (E402 remained) * fix some typos. Validate with the original repo on brooklyn.png (>95% keypoints/descriptors are the same). Successfully run on CPU but the results seem not to match very well * remove a print
* Add pipelines for Aachen, CMU, RobotCar, Cambridge, 7Scenes * Add prepend_camera_name argument * Minor fixes * Add SfM correction with dense depth * Batch conversion * Remove notebook Aachen v1.1
…76) * Move the COLMAP .bin files to the top level SfM directory * Update the notebooks * Propagate the changes to the new pipelines * Remove the Aachen v1.1 notebook again
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.