DeepClean: Integrated Distortion Identification and Algorithm Selection for Rectifying Image Corruptions
This addresses the need for efficient and adaptable image processing pipelines in vision applications, though it is incremental as it builds on existing algorithms with a novel selection mechanism.
The paper tackles the problem of automated image distortion classification and rectification by proposing a two-level sequential planning approach that dynamically selects algorithms based on input images, demonstrating improvements in object detection on the COCO dataset with various distortions.
Distortion identification and rectification in images and videos is vital for achieving good performance in downstream vision applications. Instead of relying on fixed trial-and-error based image processing pipelines, we propose a two-level sequential planning approach for automated image distortion classification and rectification. At the higher level it detects the class of corruptions present in the input image, if any. The lower level selects a specific algorithm to be applied, from a set of externally provided candidate algorithms. The entire two-level setup runs in the form of a single forward pass during inference and it is to be queried iteratively until the retrieval of the original image. We demonstrate improvements compared to three baselines on the object detection task on COCO image dataset with rich set of distortions. The advantage of our approach is its dynamic reconfiguration, conditioned on the input image and generalisability to unseen candidate algorithms at inference time, since it relies only on the comparison of their output of the image embeddings.