Reproduce “Object Pose from 2-D to 3-D Point and Line Correspondences” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Thai Quynh Phong, Radu Horaud, Adnan Yassine, Pham Dinh Tao
The authors estimate rigid-object position and orientation from a known 3-D model and matched image points or lines. They encode rotation and translation in a dual-number quaternion, making constraints quadratic, then minimize squared errors with a trust-region method, assuming known camera intrinsics. In tests, line-based translation error was 0.0028 cm at 0.50-pixel noise, versus 0.9617 cm for a linear baseline; differing intrinsic handling limits comparison.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.