World From Blur
What can we tell from a single motion-blurred image? We show in this paper that a 3D scene can be revealed. Unlike prior methods that focus on producing a deblurred image, we propose to estimate and take advantage of the hidden message of a blurred image, the relative motion trajectory, to restore the 3D scene collapsed during the exposure process. To this end, we train a deep network that jointly predicts the motion trajectory, the deblurred image, and the depth one, all of which in turn form a collaborative and self-supervised cycle that supervise one another to reproduce the input blurred image, enabling plausible 3D scene reconstruction from a single blurred image. We test the proposed model on several large-scale datasets we constructed based on benchmarks, as well as real-world blurred images, and show that it yields very encouraging quantitative and qualitative results.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Scene ReconstructionSimilar Papers 제목 키워드 기반
Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms
Numerous learning-based approaches to single image deblurring for camera and object motion blurs have recently been proposed. To generalize such approaches to real-world blurs, large datasets of real blurred images and t…
BenchmarkingDeblurringImage DeblurringSingle Image DeblurringGS-RealBlur: A Flexible Data Acquisition Framework for Real-World Image Deblurring
High-quality, large-scale paired data is essential for training learning-based image deblurring models. However, synthetic blurry images generally lack realism, while real-world captured images require complex and inflex…
Image DeblurringTowards Real-World Video Deblurring by Exploring Blur Formation Process
This paper aims at exploring how to synthesize close-to-real blurs that existing video deblurring models trained on them can generalize well to real-world blurry videos. In recent years, deep learning-based approaches ha…
DeblurringVideo DeblurringMotion Deblurring with Real Events
In this paper, we propose an end-to-end learning framework for event-based motion deblurring in a self-supervised manner, where real-world events are exploited to alleviate the performance degradation caused by data inco…
DeblurringRethinking Blur Synthesis for Deep Real-World Image Deblurring
In this paper, we examine the problem of real-world image deblurring and take into account two key factors for improving the performance of the deep image deblurring model, namely, training data synthesis and network arc…
DeblurringImage Deblurring