Metraipolis › archive › dc_b991ef57bc98

TrafficImag: A Benchmark for Counterfactual Roadside Traffic Video Generation — arXiv:2609.30722

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30722
License (as archived)
CC0-1.0
Archived
2026-10-08T01:39:28.106Z
SHA-256 of the archived text
7ed9f9f47c18ecb4d75d7fb3634a07d6fac7652c5740bc3df97d9fc03c7cdb02
Stable URL of this page
https://metraipolis.com/documento/dc_b991ef57bc98

How to cite

TrafficImag: A Benchmark for Counterfactual Roadside Traffic Video Generation — arXiv:2609.30722 — arXiv (en), https://arxiv.org/abs/2609.30722 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b991ef57bc98 (Metraipolis archive dc_b991ef57bc98, sha256 7ed9f9f47c18ecb4d75d7fb3634a07d6fac7652c5740bc3df97d9fc03c7cdb02)
BibTeX
@misc{dcb991ef57bc98,
  title = {TrafficImag: A Benchmark for Counterfactual Roadside Traffic Video Generation — arXiv:2609.30722},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30722},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b991ef57bc98; sha256 7ed9f9f47c18ecb4d75d7fb3634a07d6fac7652c5740bc3df97d9fc03c7cdb02},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30722. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Existing roadside traffic datasets support perception, forecasting, and visual question answering, but they do not evaluate counterfactual video generation, in which a selected actor is modified and the generated future should remain consistent with road topology and unrelated traffic. We introduce TrafficImag, the first benchmark for counterfactual roadside traffic video generation. TrafficImag combines a large-scale roadside dataset (9,022 annotated images, 7,043 deduplicated video clips, and 31,145 actor-centered history-future samples) with an executable protocol that supports behavior reasoning, intervention-aware image editing, and conditional video generation. Each intervention is represented as an actor-level program describing the target actor, intended behavior, legal route, interaction order, and temporal constraints, enabling a unified evaluation interface across heterogeneous foundation models. TrafficImag evaluates four complementary validity dimensions: initial-state correctness, route and behavior validity, interaction consistency, and non-target preservation, and considers an end-to-end counterfactual successful only when all four are satisfied. Across state-of-the-art foundation models, the strongest reasoner reaches 80.4% macro F1, the complete condition interface raises end-to-end success from 23.3% to 55.0% for the best generator. Oracle studies further show that conditional video execution is the primary remaining bottleneck. TrafficImag provides a reproducible benchmark for evaluating and diagnosing counterfactual traffic video generation beyond perceptual video quality.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.30722 — 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 2026-10-08T01:12:14.472Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).