CVFeb 9, 2024

Spatially-Attentive Patch-Hierarchical Network with Adaptive Sampling for Motion Deblurring

arXiv:2402.06117v1h-index: 41
AI Analysis

It addresses motion deblurring for computer vision applications, offering incremental improvements in performance-complexity trade-offs.

The paper tackles motion deblurring in dynamic scenes by proposing a pixel-adaptive and feature-attentive design to handle large blur variations, achieving favorable performance against state-of-the-art algorithms on benchmarks.

This paper tackles the problem of motion deblurring of dynamic scenes. Although end-to-end fully convolutional designs have recently advanced the state-of-the-art in non-uniform motion deblurring, their performance-complexity trade-off is still sub-optimal. Most existing approaches achieve a large receptive field by increasing the number of generic convolution layers and kernel size. In this work, we propose a pixel adaptive and feature attentive design for handling large blur variations across different spatial locations and process each test image adaptively. We design a content-aware global-local filtering module that significantly improves performance by considering not only global dependencies but also by dynamically exploiting neighboring pixel information. We further introduce a pixel-adaptive non-uniform sampling strategy that implicitly discovers the difficult-to-restore regions present in the image and, in turn, performs fine-grained refinement in a progressive manner. Extensive qualitative and quantitative comparisons with prior art on deblurring benchmarks demonstrate that our approach performs favorably against the state-of-the-art deblurring algorithms.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes