Geodesic star convexity for interactive image segmentation

By Varun Gulshan, Carsten Rother, Antonio Criminisi, Andrew Blake, Andrew Zisserman. 2010

448 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Ming-Hsuan Yang
3. Dacheng Tao
4. Xiaogang Wang
5. Jitendra Malik
6. Alan L. Yuille
7. Trevor Darrell
8. Jiashi Feng

Citations in the corpus

• SimpleClick: Interactive Image Segmentation with Simple Vision Transformers (2022, background): “Early works [5,14,16,37] tackle this problem by optimizing a graph defined over image pixels.”
• FocalClick: Towards Practical Interactive Image Segmentation (2022, background): “Before the era of deep learning, researchers [11, 12, 19, 34] take interactive segmentation as an optimization procedure.”
• Reviving Iterative Training with Mask Guidance for Interactive Segmentation (2021, methodology): “Scribbles are used in many early works [5, 15, 16, 17, 26].”
• Deep Interactive Object Selection (2016, methodology): “Strokebased methods are popular, and use a number of underlying algorithms, including normalized cuts [22], graph cut [2, 11, 26], geodesics [1, 4], the combination of graph cut and geodesics [20, 9] and random walks [8].”
• Perceptually Inspired Layout-Aware Losses for Image Segmentation (2014, methodology): “Following [9] we define the distance from a pixel to the seed region as the minimum length of a discrete path that leads form the pixel to the region, where the length of each path is defined as follows:”
• Learning an interactive segmentation system (2009, background): “This corresponds with the findings in [13] on a different dataset.”
• Exploring Compositional High Order Pattern Potentials for Structured Output Learning (2013, background): “convexity [5], connectivity [32, 23], and a bounding box occupancy constraint [17].”
• TouchCut: Fast image and video segmentation using single-touch interaction (2014, background): “6 on both a qualitative and quantitative basis, concluding in Sec.”
• Conditional Diffusion for Interactive Segmentation (2021, background): “Geodesics [7] calculates geodesic between clicked points and other pixels to predict segments with minimum energy cost.”
• Interactive Image Segmentation via Backpropagating Refinement Scheme (2019, methodology): “Experimental results show that the proposed BRS algorithm outperforms the conventional algorithms [11, 10, 3, 52, 50, 2, 27, 26] on the GrabCut [42], Berkeley [34], DAVIS [37], and SBD [12] datasets.”
• Learning to segment under various forms of weak supervision (2015, methodology): “Supervision in the form of partial labels has been effectively utilized in interactive object segmentation via graph-cuts [3], random walks [12], geodesic shortest path [2], and geodesic star convexity [15].”
• Regional Interactive Image Segmentation Networks (2017, unknown): “(e) MS COCO unseen categories RIS-Net (ours) iFCN [29] Random walker [11] Euclidean star convexity [12] Geodesic star convexity [12] Geodesic matting [1] Growcut [26] Graph cut [4]”
• Interactive Image Segmentation With First Click Attention (2020, background): “[19] and Bai et al .”
• MultiSeg: Semantically Meaningful, Scale-Diverse Segmentations From Minimal User Input (2019, background): “Various forms of priors have also been proposed to further improve the segmentation performance [10, 12, 35].”