XM4D: 4D Reconstruction through Certifiable Geometric Optimization
XM4D: 4D Reconstruction through Certifiable Geometric Optimization
This research introduces XM4D, a framework for accurate and efficient 4D reconstruction that guarantees global optimality by separating camera motion estimation from non-rigid deformation into structured quadratically constrained quadratic programs (QCQP) solvable with semidefinite programming relaxations. The method lifts static point tracks to 3D using depth prediction models, reduces the problem to rotation-only QCQPs for both stages, and initializes dynamic Gaussian splatting for photometric refinement. Extensive experiments across seven benchmarks demonstrate accurate camera motion estimation on static and dynamic scenes, efficient optimization scaling to thousands of frames, and state-of-the-art novel-view rendering quality.
The paper proposes XM4D, a framework for certifiably globally optimal 4D reconstruction by formulating camera motion and non-rigid deformation as quadratically constrained quadratic programs (QCQP) solvable via semidefinite programming relaxations; experiments on seven benchmarks report accurate motion estimation and state-of-the-art novel-view rendering quality.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
Source：arXiv Robotics — research abstracts · arxiv.org