STEREOFLOW: Progressive Stereo Matching with StereoDiT and Transition Flow Matching

• URL: http://arxiv.org/abs/2607.19986v1
• Date: Wed, 22 Jul 2026 10:19:43 GMT
• Title: STEREOFLOW: Progressive Stereo Matching with StereoDiT and Transition Flow Matching
• Abstract summary: We introduce a prior-guided generative framework that integrates deterministic matching regression and generative distribution modeling.<n>The proposed StereoFlow establishes multiple state-of-the-art results across benchmarks, including Scene Flow, KITTI, ETH3D, and Middlebury.
• Score: 45.06621486586422
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• StereoDiffuer: Diffusion-based Progressive Geometry Modeling with Saliency Attention Perception for Stereo Matching [4.145113170351399]
  We propose StereoDiffuer, an iterative diffusion-based stereo matching framework.<n>It explicitly models geometric details and progressively refines disparity estimates.<n>Results on the Scene Flow and KITTI benchmarks demonstrate the effectiveness of the proposed framework.
  arXiv  Detail & Related papers  (2026-08-22T01:04:27Z)
• Hierarchical Flow Matching for 3D Point Cloud Generation [3.451986888321395]
  Existing flow-based methods rely on continuous normalizing flows (CNFs) that demand expensive ODE solving and trace estimation during training.<n>We propose Hierarchical Flow Matching (HFM) that extends flow matching to bilevel structure for unconditional 3D point cloud generation.<n>The resulting straight OT paths enable efficient sampling with as few as 15 Euler steps per flow, while the structured latent space supports downstream tasks including classification.
  arXiv  Detail & Related papers  (2026-08-06T03:23:49Z)
• SurF: A Generative Model for Multivariate Irregular Time Series Forecasting [9.605729240308543]
  We propose SurF, a generative model that learns between event sequences and i.i.d. unit-rate exponential noise.<n>On six real-world benchmarks, SurF achieves the best reported time RMSE on Earthquake, Retweet, and Taobao.<n>Under a strict leave-one-out protocol, SurF beats every classical and neural-autoregressive baseline on 5/6 datasets.
  arXiv  Detail & Related papers  (2026-05-13T19:46:48Z)
• Improving Progressive Generation with Decomposable Flow Matching [50.63174319509629]
  Decomposable Flow Matching (DFM) is a simple and effective framework for the progressive generation of visual media.<n>On Imagenet-1k 512px, DFM achieves 35.2% improvements in FDD scores over the base architecture and 26.4% over the best-performing baseline.
  arXiv  Detail & Related papers  (2025-06-24T17:58:02Z)
• Divide-and-Conquer: Confluent Triple-Flow Network for RGB-T Salient Object Detection [70.84835546732738]
  RGB-Thermal Salient Object Detection aims to pinpoint prominent objects within aligned pairs of visible and thermal infrared images.<n>Traditional encoder-decoder architectures may not have adequately considered the robustness against noise originating from defective modalities.<n>We propose the ConTriNet, a robust Confluent Triple-Flow Network employing a Divide-and-Conquer strategy.
  arXiv  Detail & Related papers  (2024-12-02T14:44:39Z)
• Match-Stereo-Videos: Bidirectional Alignment for Consistent Dynamic Stereo Matching [17.344430840048094]
  Recent learning-based methods prioritize optimal performance on a single stereo pair, resulting in temporal inconsistencies. We develop a bidirectional alignment mechanism for adjacent frames as a fundamental operation. Unlike the existing methods, we model this task as local matching and global aggregation.
  arXiv  Detail & Related papers  (2024-03-16T01:38:28Z)
• Unifying Flow, Stereo and Depth Estimation [121.54066319299261]
  We present a unified formulation and model for three motion and 3D perception tasks. We formulate all three tasks as a unified dense correspondence matching problem. Our model naturally enables cross-task transfer since the model architecture and parameters are shared across tasks.
  arXiv  Detail & Related papers  (2022-11-10T18:59:54Z)
• AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach [50.855679274530615]
  We present a novel domain-adaptive approach called AdaStereo to align multi-level representations for deep stereo matching networks. Our models achieve state-of-the-art cross-domain performance on multiple benchmarks, including KITTI, Middlebury, ETH3D and DrivingStereo. Our method is robust to various domain adaptation settings, and can be easily integrated into quick adaptation application scenarios and real-world deployments.
  arXiv  Detail & Related papers  (2021-12-09T15:10:47Z)
• Consistency Guided Scene Flow Estimation [159.24395181068218]
  CGSF is a self-supervised framework for the joint reconstruction of 3D scene structure and motion from stereo video. We show that the proposed model can reliably predict disparity and scene flow in challenging imagery. It achieves better generalization than the state-of-the-art, and adapts quickly and robustly to unseen domains.
  arXiv  Detail & Related papers  (2020-06-19T17:28:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.