Metraipolis › archive › dc_a129cf62ae09

Inter-3D VQA: A Roadside Multimodal Benchmark for 3D Spatiotemporally Grounded Visual Question Answering — arXiv:2608.28762

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.28762
License (as archived): CC0-1.0
Archived: 2026-10-17T09:53:19.126Z
SHA-256 of the archived text: be4a8ba82d01aadfdd1de084bf21c50dec0dd6f44a846ae2cb541687262af7ed
Stable URL of this page: https://metraipolis.com/documento/dc_a129cf62ae09

How to cite

Inter-3D VQA: A Roadside Multimodal Benchmark for 3D Spatiotemporally Grounded Visual Question Answering — arXiv:2608.28762 — arXiv (en), https://arxiv.org/abs/2608.28762 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a129cf62ae09 (Metraipolis archive dc_a129cf62ae09, sha256 be4a8ba82d01aadfdd1de084bf21c50dec0dd6f44a846ae2cb541687262af7ed)

BibTeX

@misc{dca129cf62ae09,
  title = {Inter-3D VQA: A Roadside Multimodal Benchmark for 3D Spatiotemporally Grounded Visual Question Answering — arXiv:2608.28762},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28762},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a129cf62ae09; sha256 be4a8ba82d01aadfdd1de084bf21c50dec0dd6f44a846ae2cb541687262af7ed},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28762. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in visual question answering (VQA) and multimodal large language models (MLLMs) have enabled natural-language reasoning over traffic scenes. However, existing benchmarks are largely built from ego-vehicle views or 2D roadside videos, limiting their ability to evaluate 3D-grounded reasoning over real-world distances, trajectories, infrastructure topology, and safety-critical interactions. We introduce Inter-3D VQA, a large-scale roadside multimodal benchmark for 3D spatiotemporally grounded VQA at intersections. Built from synchronized point clouds and multi-view images, Inter-3D VQA contains 407K QA pairs covering lane-level positions, object relationships, motion patterns, and near-miss-oriented interaction reasoning. We further propose Inter-Geo, an MLLM baseline that integrates object- and scene-level aligned LiDAR representations, and Inter-Metrics, a unified evaluation framework for textual consistency, numerical accuracy, and semantic correctness. Experiments show that Inter-Geo outperforms image-based VLMs, especially on grounded spatial and temporal reasoning tasks. Our benchmark and codes are available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.28762 — 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 2026-10-17T09:28:47.951Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).