EvBS is proposed, an event-guided blur synthesis framework that generates diverse training pairs for calibrating pre-trained models to the target domain and effectively enhances the robustness of existing deblurring models on unseen testing datasets.
Abstract
Motion deblurring has achieved remarkable progress with deep learning, yet pre-trained deblurring models often suffer from performance degradation in real-world scenarios due to the domain shift between training and testing distributions. To remedy this, we propose EvBS, an event-guided blur synthesis framework that generates diverse training pairs for calibrating pre-trained models to the target domain. While existing methods are constrained by the inherent entanglement between motion and visual content, our method leverages the high temporal resolution of event cameras to effectively decouple them. This enables us to utilize not only the intrinsic motion that is inherent to the given content but also extrinsic motion transferred from different sources within the target domain, thereby facilitating effective adaptation via fine-tuning. Specifically, EvBS comprises two complementary strategies: Intrinsic-Blur Synthesis, which blurs sharp contents with their own motion patterns, and Extrinsic-Blur Synthesis, which transfers motion from blurry patches to distinct sharp content. This approach generates a diverse set of training pairs that break the inherent constraints of naturally coupled motion and content, resulting in enhanced domain-adaptive deblurring performance. Extensive experiments on multiple benchmarks demonstrate that EvBS effectively enhances the robustness of existing deblurring models on unseen testing datasets.
An efficient generative framework designed to improve in-the-wild robustness under diverse real capture conditions and demonstrate strong perceptual quality, semantic fidelity, and temporal consistency on unseen videos, as well as improved robustness in downstream 3D reconstruction under severe motion blur.
Defocus deblurring is a challenging task due to spatially varying blur and limited aligned training data. Existing datasets suffer from insufficient scene diversity and misalignment between defocused and all-in-focus images, restricting network performance. Additionally, single-stage autoencoders often fall into local optima, causing under-recovery and artifacts. To address these problems, we propose a novel multi-stage restoration framework guided by information from a single all-in-focus image. First, rendering synthesis adds defocus attributes to all-in-focus images, solving data alignment and consistency issues. Second, a stacked autoencoder guided by defocus degree maps handles spatially varying blur hierarchically. Finally, Feature Selection and Feature Attention Modules discriminatively select valuable information and transmit first-stage features to later stages for better region-wise deblurring. Extensive experiments on multiple test sets validate that our method achieves state-of-the-art performance both quantitatively and qualitatively. Specifically, on the DPDD dataset, our method achieves 29.41 dB PSNR and 0.886 SSIM, outperforming the previous best method by 0.19 dB; on the RealDOF dataset, it achieves 23.65 dB PSNR, surpassing IFANet by 0.89 dB.
Yiming Zhong, Jifeng Chen· International Conference on...· 0 citations
Neural Radiance Fields (NeRF) achieves impressive novel view rendering performance by learning an implicit 3D representation from sparse view images. However, it is difficult to reconstruct a sharp NeRF from blurry input that often occurs in the wild. To solve this problem, we propose a novel Efficient Event-Enhanced NeRF (E3NeRF) framework, reconstructing a sharp NeRF by utilizing both blurry images and corresponding event streams. A blur rendering loss and an event rendering loss are introduced, which guide the NeRF training via modeling the physical image motion blur process and the event generation process, respectively. To improve the efficiency of the framework, we further leverage the latent spatial-temporal blur information in the event stream to evenly distribute training over temporal blur and focus training on spatial blur. Moreover, a camera pose estimation framework for real-world data is built with the guidance of the events, generalizing the method to more practical applications. Compared to previous image-based and event-based NeRF works, our framework makes more profound use of the internal relationship between events and images. Extensive experiments on both synthetic data and real-world data demonstrate that E3NeRF can effectively learn a sharp NeRF from blurry images, especially for high-speed non-uniform motion and low-light scenes.
Yunshan Qi, Jia Li, Yifan Zhao et al.· IEEE Transactions on Pattern...· 0 citations
Event cameras offer microsecond-level temporal resolution and high dynamic range, potentially facilitating motion-blur-free panoramic imaging from fast rotational scanning. Nonetheless, existing optimization-based methods remain computationally demanding, while prior learning-based reconstruction methods are largely designed for perspective imagery and lack geometry-aware support for panoramic outputs. We present E2Pano, a geometry-guided event-to-panorama pipeline with an end-to-end learnable photometric reconstruction stage. Our framework preserves real spherical coordinates from geometric mapping throughout the pipeline, employs a lightweight enhancement module with frequency-domain supervision to bridge the event-image domain gap, and leverages a spherical Transformer with 3D positional embeddings for photometric reconstruction. Experiments on synthetic data and captured rotational scans show improved reconstruction quality and lower photometric reconstruction cost than optimization-based baselines, together with encouraging transfer to real captures under our acquisition protocol despite training purely on synthetic data. Additionally, we construct PanoScan, a dataset with 4,370 synthetic and 30 real-world panoramic scenes paired with event streams. Our dataset and code will be released.
Zhenyang Li, Zongqi He, Jia Pan et al.· 0 citations
This work proposes an adapter-based framework that incorporates event-derived cues into a pre-trained image-to-video diffusion model with minimal architectural changes and consistently outperforms existing state-of-the-art approaches.
Guixu Lin, Yuyang Yu, Xiang Ji et al.· 0 citations
An adaptive multi-scale decoding framework that effectively balances global context with fine-grained detail is proposed that exhibits superior robustness and generalization across diverse domains, effectively alleviating limitations of existing fusion-based approaches.
