DSI-Bench: A Benchmark for Dynamic Spatial Intelligence
This addresses the need for better evaluation of dynamic spatial intelligence in AI models, though it is incremental as it focuses on benchmarking rather than novel method development.
The paper tackled the problem of limited dynamic spatial reasoning in vision-language and visual expertise models by introducing DSI-Bench, a benchmark with nearly 1,000 dynamic videos and over 1,700 questions, revealing that models often conflate observer and object motion and fail in dynamic scenarios.
Reasoning about dynamic spatial relationships is essential, as both observers and objects often move simultaneously. Although vision-language models (VLMs) and visual expertise models excel in 2D tasks and static scenarios, their ability to fully understand dynamic 3D scenarios remains limited. We introduce Dynamic Spatial Intelligence and propose DSI-Bench, a benchmark with nearly 1,000 dynamic videos and over 1,700 manually annotated questions covering nine decoupled motion patterns of observers and objects. Spatially and temporally symmetric designs reduce biases and enable systematic evaluation of models' reasoning about self-motion and object motion. Our evaluation of 14 VLMs and expert models reveals key limitations: models often conflate observer and object motion, exhibit semantic biases, and fail to accurately infer relative relationships in dynamic scenarios. Our DSI-Bench provides valuable findings and insights about the future development of general and expertise models with dynamic spatial intelligence.