English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We present a method named iComMa to address the 6D pose estimation problem incomputer vision. The conventional pose estimation methods typically rely on thetarget's CAD model or necessitate specific network training tailored toparticular object classes. Some existing methods address mesh-free 6D poseestimation by employing the inversion of a Neural Radiance Field (NeRF), aimingto overcome the aforementioned constraints. However, it still suffers fromadverse initializations. By contrast, we model the pose estimation as theproblem of inverting the 3D Gaussian Splatting (3DGS) with both the comparingand matching loss. In detail, a render-and-compare strategy is adopted for theprecise estimation of poses. Additionally, a matching module is designed toenhance the model's robustness against adverse initializations by minimizingthe distances between 2D keypoints. This framework systematically incorporatesthe distinctive characteristics and inherent rationale of render-and-compareand matching-based approaches. This comprehensive consideration equips theframework to effectively address a broader range of intricate and challengingscenarios, including instances with substantial angular deviations, all whilemaintaining a high level of prediction accuracy. Experimental resultsdemonstrate the superior precision and robustness of our proposed jointlyoptimized framework when evaluated on synthetic and complex real-world data inchallenging scenarios.

iComMa: Inverting 3D Gaussians Splatting for Camera Pose Estimation via Comparing and Matching