Stripformer: Strip Transformer for Fast Image Deblurring
It addresses motion blur degradation in images for computer vision applications, presenting an incremental improvement with efficiency gains.
The paper tackles image deblurring in dynamic scenes by proposing Stripformer, a transformer-based model that uses intra- and inter-strip attention to handle directional and non-uniform blur, achieving favorable performance against state-of-the-art models.
Images taken in dynamic scenes may contain unwanted motion blur, which significantly degrades visual quality. Such blur causes short- and long-range region-specific smoothing artifacts that are often directional and non-uniform, which is difficult to be removed. Inspired by the current success of transformers on computer vision and image processing tasks, we develop, Stripformer, a transformer-based architecture that constructs intra- and inter-strip tokens to reweight image features in the horizontal and vertical directions to catch blurred patterns with different orientations. It stacks interlaced intra-strip and inter-strip attention layers to reveal blur magnitudes. In addition to detecting region-specific blurred patterns of various orientations and magnitudes, Stripformer is also a token-efficient and parameter-efficient transformer model, demanding much less memory usage and computation cost than the vanilla transformer but works better without relying on tremendous training data. Experimental results show that Stripformer performs favorably against state-of-the-art models in dynamic scene deblurring.