PatchPerPix for Instance Segmentation
It addresses instance segmentation in microscopy and biological imaging, offering a novel approach for handling sophisticated shapes and dense clusters, which is incremental in improving performance on specific domains.
The paper tackles instance segmentation for complex object shapes in dense clusters by proposing a non-iterative method based on dense local shape descriptors, achieving state-of-the-art results on four benchmarks including ISBI 2012 EM and BBBC010 C. elegans datasets.
We present a novel method for proposal free instance segmentation that can handle sophisticated object shapes which span large parts of an image and form dense object clusters with crossovers. Our method is based on predicting dense local shape descriptors, which we assemble to form instances. All instances are assembled simultaneously in one go. To our knowledge, our method is the first non-iterative method that yields instances that are composed of learnt shape patches. We evaluate our method on a diverse range of data domains, where it defines the new state of the art on four benchmarks, namely the ISBI 2012 EM segmentation benchmark, the BBBC010 C. elegans dataset, and 2d as well as 3d fluorescence microscopy data of cell nuclei. We show furthermore that our method also applies to 3d light microscopy data of Drosophila neurons, which exhibit extreme cases of complex shape clusters