PhasorNet: Learning Structure from Frequency for Real-Time Stereo Matching

2026-08-30

AI Summary

为解决立体匹配中细结构等区域的挑战，提出PhasorNet框架，利用频率域线索增强几何区分，并通过多尺度边缘引导高误差区域损失优化训练。

Abstract

Accurate stereo matching remains challenging in ill-posed regions such as fine structures, reflective, or transparent objects, where appearance cues are often ambiguous or unreliable. To tackle this, we propose PhasorNet, a lightweight yet powerful framework that boosts geometric discrimination via frequency-domain cues. At its core, the Phase-Augmented Transformer (PAT) injects Fourier-derived phase information into the attention mechanism, yielding photometrically robust, structure-preserving features that prioritize structural consistency in difficult areas. Additionally, we develop a Geometry-Context Fusion Refinement Module (GCFRM) that combines a full-resolution convolutional stream with a lightweight attention-based stream (leveraging WQA and CDGA blocks) to efficiently preserve fine details and object boundaries without excessive overhead. Training is further enhanced by a multi-scale Edge-guided High-Error Region (EHR) loss that adaptively focuses optimization on high-error and edge regions, guiding hierarchical cost volume refinement. With only 5.3M parameters, PhasorNet achieves state-of-the-art performance on the challenging ETH3D benchmark while exhibiting excellent cross-domain generalization on KITTI, delivering an efficient and practical solution for accurate real-time stereo matching.

Problem

• stereo matching
• ill-posed regions
• fine structures
• reflective objects
• transparent objects

Innovation

• Phase-Augmented Transformer
• Geometry-Context Fusion Refinement Module
• Edge-guided High-Error Region loss