Meta Transferring for Deblurring
Most previous deblurring methods were built with a generic model trained on blurred images and their sharp counterparts. However, these approaches might have sub-optimal deblurring results due to the domain gap between the training and test sets. This paper proposes a reblur-deblur meta-transferring scheme to realize test-time adaptation without using ground truth for dynamic scene deblurring. Since the ground truth is usually unavailable at inference time in a real-world scenario, we leverage the blurred input video to find and use relatively sharp patches as the pseudo ground truth. Furthermore, we propose a reblurring model to extract the homogenous blur from the blurred input and transfer it to the pseudo-sharps to obtain the corresponding pseudo-blurred patches for meta-learning and test-time adaptation with only a few gradient updates. Extensive experimental results show that our reblur-deblur meta-learning scheme can improve state-of-the-art deblurring models on the DVD, REDS, and RealBlur benchmark datasets.
Code (1)
Tasks
DeblurringMeta-LearningTest-time AdaptationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Test-Time Fast Adaptation for Dynamic Scene Deblurring via Meta-Auxiliary Learning
In this paper, we tackle the problem of dynamic scene deblurring. Most existing deep end-to-end learning approaches adopt the same generic model for all unseen test images. These solutions are sub-optimal, as they fa…
Auxiliary LearningDeblurringTest-time AdaptationExplore Image Deblurring via Blur Kernel Space
This paper introduces a method to encode the blur operators of an arbitrary dataset of sharp-blur image pairs into a blur kernel space. Assuming the encoded kernel space is close enough to in-the-wild blur operators, we …
Blind Image DeblurringDeblurringFacial Expression Recognition (FER)Image DeblurringExplore Image Deblurring via Encoded Blur Kernel Space
This paper introduces a method to encode the blur operators of an arbitrary dataset of sharp-blur image pairs into a blur kernel space. Assuming the encoded kernel space is close enough to in-the-wild blur operators,…
Blind Image DeblurringDeblurringImage DeblurringTransferring Hierarchical Structure with Dual Meta Imitation Learning
Hierarchical Imitation learning (HIL) is an effective way for robots to learn sub-skills from long-horizon unsegmented demonstrations. However, the learned hierarchical structure lacks the mechanism to transfer across mu…
Few-Shot Imitation LearningImitation LearningMeta-LearningMetaXT: Meta Cross-Task Transfer between Disparate Label Spaces
Albeit the universal representational power of pre-trained language models, adapting them onto a specific NLP task still requires a considerably large amount of labeled data. Effective task fine-tuning meets challenges w…
Language ModelingLanguage Modelling