ProAlignNet : Unsupervised Learning for Progressively Aligning Noisy Contours

TL;DR

ProAlignNet is an unsupervised ConvNet that progressively aligns noisy, partial contours using a novel multi-scale approach and a shape-sensitive loss, outperforming existing methods in real-world applications.

Contribution

Introduces ProAlignNet, a novel unsupervised ConvNet architecture that aligns complex, noisy contours through multi-scale transformations and a new shape-aware loss function.

Findings

ProAlignNet effectively aligns noisy contours in simulated and real-world datasets.

It outperforms state-of-the-art methods in geo-parcel and segmentation label refinement.

The model is robust to noise and missing parts in contour data.

Abstract

Contour shape alignment is a fundamental but challenging problem in computer vision, especially when the observations are partial, noisy, and largely misaligned. Recent ConvNet-based architectures that were proposed to align image structures tend to fail with contour representation of shapes, mostly due to the use of proximity-insensitive pixel-wise similarity measures as loss functions in their training processes. This work presents a novel ConvNet, "ProAlignNet" that accounts for large scale misalignments and complex transformations between the contour shapes. It infers the warp parameters in a multi-scale fashion with progressively increasing complex transformations over increasing scales. It learns --without supervision-- to align contours, agnostic to noise and missing parts, by training with a novel loss function which is derived an upperbound of a proximity-sensitive and local shape-dependent similarity metric that uses classical Morphological Chamfer Distance Transform. We evaluate the reliability of these proposals on a simulated MNIST noisy contours dataset via some basic sanity check experiments. Next, we demonstrate the effectiveness of the proposed models in two real-world applications of (i) aligning geo-parcel data to aerial image maps and (ii) refining coarsely annotated segmentation labels. In both applications, the proposed models consistently perform superior to state-of-the-art methods.