Summary of Changes

Hello @sarlinpe, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request enhances the LightGlue feature matching process by incorporating gravity information to intelligently rotate image inputs. By aligning images based on their perceived 'up' direction, the system can achieve more robust and accurate feature correspondences, ultimately leading to better reconstruction quality. The changes involve propagating pose prior data through the matching pipeline and applying the necessary transformations within the LightGlue ONNX matcher.

Highlights

• Gravity-based Rotation for LightGlue: Implemented a mechanism to rotate LightGlue inputs (keypoints, scales, orientations, and image dimensions) based on gravity information from PosePrior.
• Improved Feature Matching Performance: The rotation aims to align images more consistently, leading to improved feature matching results, as indicated by the provided metrics showing an increase in Mean Track Length and Observations per Image.
• Integration of Pose Prior: The FeatureMatcher and its Image struct were updated to accept and utilize PosePrior information, enabling the LightGlue matcher to access gravity data.

Changelog

• src/colmap/controllers/feature_matching_utils.cc
  • Modified MatchGuided and Match methods to pass the image's PosePrior to the FeatureMatcher.
• src/colmap/feature/matcher.h
  • Added a const PosePrior* pose_prior member to the FeatureMatcher::Image struct to carry gravity information.
• src/colmap/feature/onnx_matchers.cc
  • Included colmap/geometry/pose_prior.h.
  • Implemented logic within LightGlueONNXFeatureMatcher to compute a 90-degree rotation based on the image's gravity vector if a PosePrior is available.
  • Applied the computed rotation to keypoint coordinates, scales, and orientations before feeding them to LightGlue.
  • Adjusted the reported image dimensions (width, height) to LightGlue based on whether a 90-degree rotation caused a swap of these dimensions.

Activity

• No specific activity (comments, reviews, progress) has been recorded for this pull request yet.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩