GrabCut: Interactive Foreground Extraction Using Iterated Graph Cuts

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications (2022, methodology): “The authors also proposed CNNs to first detect hand bounding boxes and then use GrabCut [56] to segment the hands.”
Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation (2023, unknown): “Interactive segmentation has a rich history, initially regarded as an optimization technique by researchers (Grady 2006; Gulshan et al. 2010; Kim, Lee, and Lee 2010; Rother, Kolmogorov, and Blake 2004).”
PseudoClick: Interactive Image Segmentation with Click Imitation (2022, methodology): “Compared with scribble-based methods [15,16], click-based interactive segmentation requires no heuristics or complex procedures to simulate user input.”
Box-supervised Instance Segmentation with Level Set Evolution (2022, methodology): “methods backbone AP AP25 AP50 AP70 AP75 GrabCut∗ [40] ResNet-101 19.”
BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation (2020, methodology): “2012) andgraph (Boykov and Jolly 2001; Rother et al. 2004) algorithms adopt hand-crafted features to solve this problem.”