SQA-3D
Emerging4papers using it
2025first seen
The SQA-3D dataset/benchmark is used to evaluate the spatial reasoning capabilities of vision-language models, focusing on tasks such as distance estimation, size comparison, and cross-view consistency.
Papers using SQA-3D (4)
- SpatialPrompting: Keyframe-driven Zero-Shot Spatial Reasoning with
Off-the-Shelf Multimodal Large Language ModelsNot All Modalities Are Equal: Instruction-Aware Gating for Multimodal VideosChat-Scene++: Exploiting Context-Rich Object Identification for 3D LLMSpaceMind: Camera-Guided Modality Fusion for Spatial Reasoning in Vision-Language Models