Metraipolis › archive › dc_aebf58916ff8

MV2: Multi-View Multi-Vehicle Driving Dataset for Novel View Synthesis — arXiv:2608.12442

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.12442
License (as archived)
CC0-1.0
Archived
2026-10-19T04:55:30.073Z
SHA-256 of the archived text
ab2d8ed6c385477caa6536b5f4ab4eb42ffad198774d7b0cf0783e9cb87b7319
Stable URL of this page
https://metraipolis.com/documento/dc_aebf58916ff8

How to cite

MV2: Multi-View Multi-Vehicle Driving Dataset for Novel View Synthesis — arXiv:2608.12442 — arXiv (en), https://arxiv.org/abs/2608.12442 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aebf58916ff8 (Metraipolis archive dc_aebf58916ff8, sha256 ab2d8ed6c385477caa6536b5f4ab4eb42ffad198774d7b0cf0783e9cb87b7319)
BibTeX
@misc{dcaebf58916ff8,
  title = {MV2: Multi-View Multi-Vehicle Driving Dataset for Novel View Synthesis — arXiv:2608.12442},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12442},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aebf58916ff8; sha256 ab2d8ed6c385477caa6536b5f4ab4eb42ffad198774d7b0cf0783e9cb87b7319},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12442. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Differentiable rendering has advanced novel view synthesis (NVS), yet applying it to real-world driving remains difficult due to sparse capture viewpoints, dynamic objects, and limited multi-trajectory data. We introduce the Multi-View Multi-Vehicle (MV2) dataset and benchmark for evaluating NVS models under large viewpoint changes in dynamic urban scenes. MV2 features synchronized captures from a car, scooter, and drone, each following distinct yet synchronized trajectories. Training NVS methods on one vehicle's camera stream and testing on another enables evaluation under substantially larger viewpoint variations than existing single-trajectory datasets. All sequences are registered via Structure-from-Motion and camera poses verified using manual pixel-level correspondence annotations, yielding 50 high-quality scenes with 12000 images. Benchmarking recent NVS and camera pose estimation methods shows that NVS performance degrades with increasing viewpoint disparity, and that feed-forward pose estimators notably lag behind optimization-based approaches, highlighting MV2 as a rigorous testbed for NVS in driving. The dataset, benchmark protocol, and project resources are available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-14 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.12442 — 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 2026-10-19T04:46:30.049Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).