STEREOFLOW: Progressive Stereo Matching with StereoDiT and Transition Flow Matching
This work addresses the regression-to-mean bias in stereo matching for 3D reconstruction, offering improved performance in ambiguous regions, but the approach is incremental as it builds on existing diffusion and flow matching techniques.
StereoFlow introduces a prior-guided generative framework for stereo matching that combines deterministic regression with generative distribution modeling, achieving state-of-the-art results on Scene Flow, KITTI, ETH3D, and Middlebury benchmarks, particularly in ambiguous and ill-posed regions.
Stereo matching is a fundamental task in 3D reconstruction. Despite remarkable advances, the prevailing paradigms formulate stereo matching as a deterministic regression problem, collapsing the multimodal distribution modeling into a single-point estimation. This formulation suffers from a regression-to-mean bias, frequently struggling with ambiguous regions. In contrast, we introduce a prior-guided generative framework that integrates deterministic matching regression and generative distribution modeling within a complementary formulation. Built upon this formulation, we introduce StereoFlow through three key components: (i) a two-stage progressive cascade matching network that progressively produces multi-resolution stereo conditions with complementary matching cues; (ii) a pixel diffusion transformer (termed StereoDiT) with a frequency-decoupled architecture for modeling correspondence ambiguity; (iii) a few-step flow matching objective (termed Transition Flow Matching) for efficient optimization. In summary, \textsc{\textbf{StereoFlow}} achieves strong geometric consistency and rich fine-grained details in ill-posed, discontinuous regions and under zero-shot generalization. Extensive experiments demonstrate that the proposed StereoFlow establishes multiple state-of-the-art results across benchmarks, including Scene Flow, KITTI, ETH3D, and Middlebury.