RED: Robust Event-Guided Motion Deblurring with Modality-Specific Disentanglement
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914373931368448 |
|---|---|
| author | Leng, Yihong Zheng, Siming Chen, Jinwei Li, Bo Li, Jiaojiao Jiang, Peng-Tao |
| author_facet | Leng, Yihong Zheng, Siming Chen, Jinwei Li, Bo Li, Jiaojiao Jiang, Peng-Tao |
| contents | Event-guided motion deblurring reconstructs sharp images using the high-temporal-resolution motion cues from event cameras. However, in real capture, thresholding-induced event under-reporting causes missing and fragmented motion cues, under which existing methods often degrade in performance due to two limitations: i) assumptions of dense and stable events, and ii) modality-indiscriminate extraction and fusion that fail to separate useful motion cues from disrupted events, allowing them to contaminate cross-modal representations. In this paper, we first introduce a Robustness-Oriented Perturbation Strategy (RPS) that mimics various trigger thresholds of dynamic vision sensors, exposing our model to diverse under-reporting patterns and thereby improving robustness under unknown conditions. Built upon this setting, we propose RED, a Robust Event-guided Deblurring network, following the principle of disentangle first and then fuse selectively. Specifically, the Modality-specific Representation Mechanism disentangles the inputs into image-semantic, event-motion, and cross-modal representations, capturing appearance, motion, and complementary interactions, respectively. With the reliable disentangled features, we selectively fuse modalities to enhance motion-sensitive areas in blurry images and enrich under-reported events with semantic context. Extensive experiments on synthetic and real-world datasets demonstrate RED consistently achieves state-of-the-art performance in terms of both accuracy and robustness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_05554 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RED: Robust Event-Guided Motion Deblurring with Modality-Specific Disentanglement Leng, Yihong Zheng, Siming Chen, Jinwei Li, Bo Li, Jiaojiao Jiang, Peng-Tao Computer Vision and Pattern Recognition Information Retrieval Event-guided motion deblurring reconstructs sharp images using the high-temporal-resolution motion cues from event cameras. However, in real capture, thresholding-induced event under-reporting causes missing and fragmented motion cues, under which existing methods often degrade in performance due to two limitations: i) assumptions of dense and stable events, and ii) modality-indiscriminate extraction and fusion that fail to separate useful motion cues from disrupted events, allowing them to contaminate cross-modal representations. In this paper, we first introduce a Robustness-Oriented Perturbation Strategy (RPS) that mimics various trigger thresholds of dynamic vision sensors, exposing our model to diverse under-reporting patterns and thereby improving robustness under unknown conditions. Built upon this setting, we propose RED, a Robust Event-guided Deblurring network, following the principle of disentangle first and then fuse selectively. Specifically, the Modality-specific Representation Mechanism disentangles the inputs into image-semantic, event-motion, and cross-modal representations, capturing appearance, motion, and complementary interactions, respectively. With the reliable disentangled features, we selectively fuse modalities to enhance motion-sensitive areas in blurry images and enrich under-reported events with semantic context. Extensive experiments on synthetic and real-world datasets demonstrate RED consistently achieves state-of-the-art performance in terms of both accuracy and robustness. |
| title | RED: Robust Event-Guided Motion Deblurring with Modality-Specific Disentanglement |
| topic | Computer Vision and Pattern Recognition Information Retrieval |
| url | https://arxiv.org/abs/2509.05554 |