Inter-3D VQA: A Roadside Multimodal Benchmark for 3D Spatiotemporally Grounded Visual Question Answering
This work introduces Inter-3D VQA, a large-scale roadside multimodal benchmark for 3D spatiotemporally grounded VQA at intersections, and proposes Inter-Geo, an MLLM baseline that integrates object- and scene-level aligned LiDAR representations, and Inter-Metrics, a unified evaluation framework for textual consistency,...