Metraipolis › archive › dc_4e350bb5bc5a

XM4D: 4D Reconstruction through Certifiable Geometric Optimization — arXiv:2611.07902

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.07902
License (as archived): CC0-1.0
Archived: 2026-11-06T14:52:07.634Z
SHA-256 of the archived text: d6c9a15fa2bac5338e572295bad142ab368114681054187fb38ed96bda3f53b4
Stable URL of this page: https://metraipolis.com/documento/dc_4e350bb5bc5a

How to cite

XM4D: 4D Reconstruction through Certifiable Geometric Optimization — arXiv:2611.07902 — arXiv (en), https://arxiv.org/abs/2611.07902 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e350bb5bc5a (Metraipolis archive dc_4e350bb5bc5a, sha256 d6c9a15fa2bac5338e572295bad142ab368114681054187fb38ed96bda3f53b4)

BibTeX

@misc{dc4e350bb5bc5a,
  title = {XM4D: 4D Reconstruction through Certifiable Geometric Optimization — arXiv:2611.07902},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07902},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e350bb5bc5a; sha256 d6c9a15fa2bac5338e572295bad142ab368114681054187fb38ed96bda3f53b4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07902. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Accurate 4D reconstruction remains challenging: jointly estimating camera motion, scene geometry, and non-rigid deformation entails highly nonconvex optimization, making global optimality difficult to guarantee. We present XM4D, a framework for accurate and efficient 4D reconstruction built upon certifiably globally optimal geometric optimization. By separating the estimation of camera motion from non-rigid deformation, we formulate both stages as structured quadratically constrained quadratic programs (QCQP) that admit semidefinite programming (SDP) relaxations and verifiable global optimality certificates. For camera motion estimation, we lift static point tracks into 3D using foundational depth prediction models and formulate a scaled bundle adjustment problem that jointly estimates camera poses, depth scales, and static landmarks. By analytically eliminating translations and landmarks, we reduce the problem to a QCQP over scaled rotations. For non-rigid reconstruction, we represent dynamic motion using an embedded deformation graph (EDG) and show that its tracking, rigidity, and temporal regularization objectives similarly reduce to a rotation-only QCQP. Both problems admit SDP relaxations that we solve efficiently with a GPU-accelerated Burer-Monteiro solver based on Riemannian optimization. The recovered geometry further initializes dynamic Gaussian splatting for photometric refinement. Extensive experiments across seven benchmarks demonstrate accurate camera motion estimation on both static and dynamic scenes, efficient optimization that scales to thousands of frames, and state-of-the-art novel-view rendering quality.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.OC, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO); Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2611.07902 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-06T14:23:27.656Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).