A Benchmark for Heterogeneous Stereo Deblurring with Physically- and Epipolar-constrained Cross Attention
This work addresses a practical problem for smartphone-based XR content capture, where existing methods fail due to hardware heterogeneity.
The paper tackles heterogeneous stereo deblurring for smartphone captures, where asymmetric blur arises from different camera modules. They introduce the HSD dataset and propose PECA, a module that improves deblurring by enforcing epipolar and physical disparity constraints, achieving consistent gains across multiple architectures.
Modern stereo-capable smartphones enable immersive XR content capture. However, hardware heterogeneity across camera modules often causes severe asymmetric blur artifacts. Existing methods and benchmarks largely assume homogeneous stereo setups and therefore do not explicitly address such asymmetric degradation. To bridge this gap, we present a dedicated framework for heterogeneous stereo deblurring. First, we introduce the heterogeneous stereo deblurring (HSD) dataset, constructed from real smartphone stereo captures via multi-frame integration. Second, we propose physically- and epipolar-constrained cross attention (PECA), a lightweight module that restricts cross-view matching to an epipolar search window bounded by a optics-derived disparity upper bound. By enforcing physically valid disparity constraints, PECA enables efficient and reliable cross-view feature fusion. Moreover, our confidence-weighted attention with residual fusion emphasizes cross-guided deblurring when correspondences are reliable, while naturally falling back to self-deblurring in occluded or unreliable regions. PECA is architecture-agnostic and consistently improves CNN-, Transformer-, and NAFNet-based baselines. Extensive experiments on HSD show that PECA-enhanced models achieve improved restoration performance with favorable efficiency.