{"ID":2865071,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.21922","arxiv_id":"2509.21922","title":"Spatial Reasoning in Foundation Models: Benchmarking Object-Centric Spatial Understanding","abstract":"Spatial understanding is a critical capability for vision foundation models. While recent advances in large vision models or vision-language models (VLMs) have expanded recognition capabilities, most benchmarks emphasize localization accuracy rather than whether models capture how objects are arranged and related within a scene. This gap is consequential; effective scene understanding requires not only identifying objects, but reasoning about their relative positions, groupings, and depth. In this paper, we present a systematic benchmark for object-centric spatial reasoning in foundation models. Using a controlled synthetic dataset, we evaluate state-of-the-art vision models (e.g., GroundingDINO, Florence-2, OWLv2) and large VLMs (e.g., InternVL, LLaVA, GPT-4o) across three tasks: spatial localization, spatial reasoning, and downstream retrieval tasks. We find a stable trade-off: detectors such as GroundingDINO and OWLv2 deliver precise boxes with limited relational reasoning, while VLMs like SmolVLM and GPT-4o provide coarse layout cues and fluent captions but struggle with fine-grained spatial context. Our study highlights the gap between localization and true spatial understanding, and pointing toward the need for spatially-aware foundation models in the community.","short_abstract":"Spatial understanding is a critical capability for vision foundation models. While recent advances in large vision models or vision-language models (VLMs) have expanded recognition capabilities, most benchmarks emphasize localization accuracy rather than whether models capture how objects are arranged and related withi...","url_abs":"https://arxiv.org/abs/2509.21922","url_pdf":"https://arxiv.org/pdf/2509.21922v1","authors":"[\"Vahid Mirjalili\",\"Ramin Giahi\",\"Sriram Kollipara\",\"Akshay Kekuda\",\"Kehui Yao\",\"Kai Zhao\",\"Jianpeng Xu\",\"Kaushiki Nag\",\"Sinduja Subramaniam\",\"Topojoy Biswas\",\"Evren Korpeoglu\",\"Kannan Achan\"]","published":"2025-09-26T06:06:19Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\"]","has_code":false}