Metraipolis › archive › dc_a49deac16fc5
MeRoPE: Metric Rotary Position Embedding for Camera-Controlled Video Generation — arXiv:2609.01252
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01252
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:13:51.060Z
- SHA-256 of the archived text
1c292887e34f5c230b034ba5bc429f4713fe122e83fc4d3c0534e557f0478fd8- Stable URL of this page
https://metraipolis.com/documento/dc_a49deac16fc5
How to cite
MeRoPE: Metric Rotary Position Embedding for Camera-Controlled Video Generation — arXiv:2609.01252 — arXiv (en), https://arxiv.org/abs/2609.01252 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a49deac16fc5 (Metraipolis archive dc_a49deac16fc5, sha256 1c292887e34f5c230b034ba5bc429f4713fe122e83fc4d3c0534e557f0478fd8)
BibTeX
@misc{dca49deac16fc5,
title = {MeRoPE: Metric Rotary Position Embedding for Camera-Controlled Video Generation — arXiv:2609.01252},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01252},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a49deac16fc5; sha256 1c292887e34f5c230b034ba5bc429f4713fe122e83fc4d3c0534e557f0478fd8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01252. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In camera-controlled video generation, geometry-aware positional encodings condition tokens on camera extrinsics and per-token viewing rays. Existing schemes, however, have a scale-dependent failure mode on real-world metric camera trajectories: homogeneous projective encodings cause attention logits and feature norms to grow unbounded with physical translation baselines. We propose MeRoPE (Metric Rotary Position Embedding), a norm-preserving relative camera encoding for attention. MeRoPE encodes relative orientations between calibrated viewing rays with orthogonal rotation blocks, maps raw metric displacements into multi-frequency rotary phases, and adds a disparity-anchored correspondence prior along the epipolar arc. This design strictly preserves feature norms, bounds pre-softmax attention logits regardless of the physical translation scale, and maintains exact invariance to global rigid coordinate changes. Across nuScenes and PanShot, which cover large-baseline trajectories and diverse camera optics, respectively, MeRoPE achieves stronger camera control than prior encodings, with the best consistency between generated camera motion and conditioning poses in both rotation and translation. Code will be made publicly available. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.01252 — 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 2026-10-17T07:00:58.974Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).