BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignment
This work addresses the problem of robust 3D perception for computer vision applications by bridging modality-specific limitations, representing a novel method rather than an incremental improvement.
The paper tackles the complementary limitations of monocular and stereo depth estimation by introducing a unified framework that iteratively aligns their latent representations, resulting in a >40% reduction in zero-shot generalization error on Middlebury and ETH3D datasets and improved handling of transparent and reflective surfaces.
Monocular and stereo depth estimation offer complementary strengths: monocular methods capture rich contextual priors but lack geometric precision, while stereo approaches leverage epipolar geometry yet struggle with ambiguities such as reflective or textureless surfaces. Despite post-hoc synergies, these paradigms remain largely disjoint in practice. We introduce a unified framework that bridges both through iterative bidirectional alignment of their latent representations. At its core, a novel cross-attentive alignment mechanism dynamically synchronizes monocular contextual cues with stereo hypothesis representations during stereo reasoning. This mutual alignment resolves stereo ambiguities (e.g., specular surfaces) by injecting monocular structure priors while refining monocular depth with stereo geometry within a single network. Extensive experiments demonstrate state-of-the-art results: \textbf{it reduces zero-shot generalization error by $\!>\!40\%$ on Middlebury and ETH3D}, while addressing longstanding failures on transparent and reflective surfaces. By harmonizing multi-view geometry with monocular context, our approach enables robust 3D perception that transcends modality-specific limitations. Codes available at https://github.com/aeolusguan/BridgeDepth.