Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguity

Depth ambiguity is a fundamental challenge in spatial scene understanding, especially in transparent scenes where single-depth estimates fail to capture full 3D structure. Existing models, limited to deterministic predictions, overlook real-world multi-layer depth. To address this, we introduce a paradigm shift from single-prediction to multi-hypothesis spatial foundation models. We first present \texttt{MD-3k}, a benchmark exposing depth biases in expert and foundational models through multi-layer spatial relationship labels and new metrics. To resolve depth ambiguity, we propose Laplacian Visual Prompting (LVP), a training-free spectral prompting technique that extracts hidden depth from pre-trained models via Laplacian-transformed RGB inputs. By integrating LVP-inferred depth with standard RGB-based estimates, our approach elicits multi-layer depth without model retraining. Extensive experiments validate the effectiveness of LVP in zero-shot multi-layer depth estimation, unlocking more robust and comprehensive geometry-conditioned visual generation, 3D-grounded spatial reasoning, and temporally consistent video-level depth inference. Our benchmark and code will be available atthis https URL.

@article{xu2025_2503.06014,
  title={ Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguity },
  author={ Xiaohao Xu and Feng Xue and Xiang Li and Haowei Li and Shusheng Yang and Tianyi Zhang and Matthew Johnson-Roberson and Xiaonan Huang },
  journal={arXiv preprint arXiv:2503.06014},
  year={ 2025 }
}