TrafficImag: A Benchmark for Counterfactual Roadside Traffic Video Generation
Quick summary
arXiv:2609.30722v1 Announce Type: cross Abstract: 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
Key takeaways
- arXiv:2609.30722v1 Announce Type: cross Abstract: 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
Why it matters
The value of this work lies as much in how it was tested as in the claim itself. Sample design, baselines, uncertainty and replication help separate a laboratory result from real-world impact.
Member comments