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

arXiv:2312.09031v2 Announce Type: replace
Abstract: We present a method named iComMa to address the 6D camera pose estimation problem in computer vision. Conventional pose estimation methods typically rely on the target's CAD model or necessitate specific network training tailored to particular object classes. Some existing methods have achieved promising results in mesh-free object and scene pose estimation by inverting the Neural Radiance Fields (NeRF). However, they still struggle with adverse initializations such as large rotations and translations. To address this …

abstract arxiv cad computer computer vision cs.cv network network training object training type via vision