AllenNeuralDynamics / AllenNeuralDynamics/Rhapso

Add intensity-based candidate matching and RANSAC over full point set for R2R

未关闭
#292 0 条评论 0 个 reaction 已指派 1 人 已被 @seanfite-alleninstitute 认领 在 GitHub 查看
主要语言
Python
星标
9
派生
3
PR 合并指标
30 天内没有已合并 PR

描述

R2R registration does not match reliably using geometry-based candidate descriptors.

Store a local intensity/context region around each detected interest point.
Generate match candidates by context-region correlation within the search radius.
Update RANSAC to seed from these candidates, then iteratively resample/refit against geometric matches from the full point sets.
Integrate a param to allow users to pick between matching approaches

贡献指南

这个仓库没有索引到贡献指南

评估

这个 Issue 还没有评估数据。

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。