Unblur-SLAM: Dense Neural SLAM for Blurry Inputs
Zhang, Qi, Rozumny, Denis, Girlanda, Francesco, Karaoglu, Sezer, Pollefeys, Marc, Gevers, Theo, Oswald, Martin R.
原文摘要
We propose Unblur-SLAM, an RGB SLAM pipeline for sharp 3D reconstruction from blurred image inputs. In contrast to previous work, our approach is able to handle different types of blur and demonstrates state-of-the-art performance in the presence of both motion blur and defocus blur. Moreover, we adjust the computation effort with the amount of blur in the input image.As a first stage, our method uses a feed-forward image deblurring model for which we propose a suitable training scheme that can improve both tracking and mapping modules.Frames that are successfully deblurred by the feed-forward network obtain refined poses and depth through local-global multi-view optimization and loop closure. Frames that fail the first stage deblurring are directly modeled through the global 3DGS representation and an additional blur network to model multiple blurred sub-frames and simulate the blur formation process in 3D space, thereby learning sharp details and refined sub-frame poses.Experiments on several real-world datasets demonstrate consistent improvements in both pose estimation and sharp reconstruction results of geometry and texture.
cs.CV
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表