Blur2seq: Blind Deblurring and Camera Trajectory Estimation from a Single Camera Motion-blurred Image
Guillermo Carbajal, Andr\'es Almansa, Pablo Mus\'e

TL;DR
Blur2seq introduces a deep learning approach that jointly estimates camera motion and restores sharp images from a single motion-blurred photo, achieving state-of-the-art results especially with severe or spatially variant blur.
Contribution
The paper presents a novel modular framework combining a neural network and model-based methods to estimate 3D camera trajectories and restore images from a single motion-blurred input.
Findings
Achieves state-of-the-art deblurring performance on synthetic and real datasets.
Effectively handles severe and spatially variant motion blur.
Provides interpretable camera motion trajectories for better understanding.
Abstract
Motion blur caused by camera shake, particularly under large or rotational movements, remains a major challenge in image restoration. We propose a deep learning framework that jointly estimates the latent sharp image and the underlying camera motion trajectory from a single blurry image. Our method leverages the Projective Motion Blur Model (PMBM), implemented efficiently using a differentiable blur creation module compatible with modern networks. A neural network predicts a full 3D rotation trajectory, which guides a model-based restoration network trained end-to-end. This modular architecture provides interpretability by revealing the camera motion that produced the blur. Moreover, this trajectory enables the reconstruction of the sequence of sharp images that generated the observed blurry image. To further refine results, we optimize the trajectory post-inference via a reblur loss,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Image Processing Techniques · Image and Video Quality Assessment · Sparse and Compressive Sensing Techniques
