A Benchmark for Heterogeneous Stereo Deblurring with Physically- and Epipolar-constrained Cross Attention

• URL: http://arxiv.org/abs/2606.25962v1
• Date: Wed, 24 Jun 2026 15:34:20 GMT
• Title: A Benchmark for Heterogeneous Stereo Deblurring with Physically- and Epipolar-constrained Cross Attention
• Abstract summary: We present a dedicated framework for heterogeneous stereo deblurring.<n>We propose physically- and epipolar-constrained cross attention (PECA)<n>PECA restricts cross-view matching to an epipolar search window bounded by a optics-derived disparity upper bound.
• Score: 3.373984146148716
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Isotropic Embedding Perturbations for Robust Vision Language Encoders [73.92626712781859]
  Aether is a simple plug-in method that applies diffusion-style random perturbations in the embedding space via controlled alpha-mixing.<n>Inspired by feature-space perturbations in language models and image degradation in generative pretraining, Aether induces mild yet effective perturbations.<n>Aether delivers consistent gains over the advanced recipe combining CutMix, Mixup, DropPath, and RandAug.
  arXiv  Detail & Related papers  (2026-09-09T15:08:05Z)
• PhasorNet: Learning Structure from Frequency for Real-Time Stereo Matching [21.209111801863546]
  PhasorNet is a powerful framework that boosts geometric discrimination via frequency-domain cues.<n>With only 5.3M parameters, PhasorNet achieves state-of-the-art performance on the challenging ETH3D benchmark.
  arXiv  Detail & Related papers  (2026-08-30T14:41:36Z)
• BenthicDINO: Physics-Informed Self-Distillation for View-Invariant Side-Scan Sonar Representations [0.0]
  We introduce a physics-informed self-distillation framework built upon the DINOv3 architecture utilizing a ConvNeXt-v2-Tiny backbone to maximize data efficiency.<n>We propose a dense, hierarchical feature fusion strategy across all four network stages to preserve fine-grained sediment details alongside deep semantic abstractions.
  arXiv  Detail & Related papers  (2026-08-24T13:11:22Z)
• Cross-Spectral Stereo Inertial Odometry [6.602180427145135]
  We present an asynchronous real-time cross-spectral visual-thermal-inertial (VTI) system that temporally decouples high-latency deep matching from high-rate state estimation.<n>Our system overcomes spectral redundancy, yielding superior accuracy in nominal daylight while ensuring robustness in visually degraded environments.
  arXiv  Detail & Related papers  (2026-06-29T04:00:59Z)
• H-OmniStereo: Zero-Shot Omnidirectional Stereo Matching with Heading-Aligned Normal Priors [39.6437115448559]
  H- OmniStereo is a zero-shot omnidirectional stereo matching framework.<n>We construct high-quality synthetic dataset comprising over 2.8 million top-bottom equirectangular stereo pairs.<n>Our approach achieves higher accuracy than existing methods on out-of-domain datasets.
  arXiv  Detail & Related papers  (2026-05-14T15:30:22Z)
• Better with Less: Tackling Heterogeneous Multi-Modal Image Joint Pretraining via Conditioned and Degraded Masked Autoencoder [34.73963627819185]
  High-resolution (HR) joint optical and synthetic aperture radar (SAR) pretraining seeks modality synergy to mutually enhance single-source representations.<n>We propose CoDe-MAE, pioneering a textitbetter synergy with less alignment philosophy.<n>CoDe-MAE successfully prevents representation degradation and establishes new state-of-the-art performance across diverse single- and bi-modal downstream tasks.
  arXiv  Detail & Related papers  (2026-04-18T10:23:00Z)
• Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereo [54.58078274676216]
  Event cameras offer an alternative visual representation with higher dynamic range free of such limitations.<n>In this paper, we introduce Bi-CMPStereo, a novel bidirectional cross-modal prompting framework.<n>Our approach learns finely aligned stereo representations within a target canonical space and integrates complementary representations by projecting each modality into both event and frame domains.
  arXiv  Detail & Related papers  (2026-04-16T17:59:58Z)
• Stereo World Model: Camera-Guided Stereo Video Generation [52.3922115596956]
  We present StereoWorld, a camera-conditioned stereo world model that jointly learns appearance and binocular geometry for end-to-end stereo video generation.<n>Unlike monocular RGB or RGBD approaches, StereoWorld operates exclusively within the RGB modality, while simultaneously grounding geometry directly from disparity.
  arXiv  Detail & Related papers  (2026-03-18T05:42:22Z)
• Rotation Equivariant Arbitrary-scale Image Super-Resolution [62.41329042683779]
  The arbitrary-scale image super-resolution (ASISR) aims to achieve arbitrary-scale high-resolution recoveries from a low-resolution input image.<n>We make efforts to construct a rotation equivariant ASISR method in this study.
  arXiv  Detail & Related papers  (2025-08-07T08:51:03Z)
• FUSE: Label-Free Image-Event Joint Monocular Depth Estimation via Frequency-Decoupled Alignment and Degradation-Robust Fusion [92.4205087439928]
  Image-event joint depth estimation methods leverage complementary modalities for robust perception, yet face challenges in generalizability.<n>We propose the Self-supervised Transfer (PST) and the FrequencyDe-coupled Fusion module (FreDF)<n>PST establishes cross-modal knowledge transfer through latent space alignment with image foundation models, effectively mitigating data scarcity.<n>FreDF explicitly decouples high-frequency edge features from low-frequency structural components, resolving modality-specific frequency mismatches.<n>This combined approach enables FUSE to construct a universal image-event that only requires lightweight decoder adaptation for target datasets.
  arXiv  Detail & Related papers  (2025-03-25T15:04:53Z)
• Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail [37.90622613373521]
  We introduce Stereo Anywhere, a novel stereo-matching framework that combines geometric constraints with robust priors from monocular depth Vision Foundation Models (VFMs)<n>We show that our synthetic-only trained model achieves state-of-the-art results in zero-shot generalization, significantly outperforming existing solutions.
  arXiv  Detail & Related papers  (2024-12-05T18:59:58Z)
• 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)
• SMD-Nets: Stereo Mixture Density Networks [68.56947049719936]
  We propose Stereo Mixture Density Networks (SMD-Nets), a simple yet effective learning framework compatible with a wide class of 2D and 3D architectures. Specifically, we exploit bimodal mixture densities as output representation and show that this allows for sharp and precise disparity estimates near discontinuities. We carry out comprehensive experiments on a new high-resolution and highly realistic synthetic stereo dataset, consisting of stereo pairs at 8Mpx resolution, as well as on real-world stereo datasets.
  arXiv  Detail & Related papers  (2021-04-08T16:15:46Z)

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.