# Deep GrabCut for Object Selection

arXiv: https://arxiv.org/abs/1707.00243 · HTML: https://mlsanity.com/paper/1707.00243/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2017.

## Built on by (most cited first, 30 of 33)

- [Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion](https://mlsanity.com/paper/2103.07941/) (2021)
- [SimpleClick: Interactive Image Segmentation with Simple Vision Transformers](https://mlsanity.com/paper/2210.11006/) (2022)
- [ScribblePrompt: Fast and Flexible Interactive Segmentation for Any Biomedical Image](https://mlsanity.com/paper/2312.07381/) (2023)
- [MIDeepSeg: Minimally Interactive Segmentation of Unseen Objects from Medical Images Using Deep Learning](https://mlsanity.com/paper/2104.12166/) (2021)
- [PseudoClick: Interactive Image Segmentation with Click Imitation](https://mlsanity.com/paper/2207.05282/) (2022)
- [EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow](https://mlsanity.com/paper/2109.09406/) (2021)
- [iSegFormer: Interactive Segmentation via Transformers with Application to 3D Knee MR Images](https://mlsanity.com/paper/2112.11325/) (2021)
- [Focused and Collaborative Feedback Integration for Interactive Image Segmentation](https://mlsanity.com/paper/2303.11880/) (2023)
- [Personal Fixations-Based Object Segmentation with Object Localization and Boundary Preservation](https://mlsanity.com/paper/2101.09014/) (2021)
- [Interactive Multi-Class Tiny-Object Detection](https://mlsanity.com/paper/2203.15266/) (2022)
- [Interactive Segmentation as Gaussian Process Classification](https://mlsanity.com/paper/2302.14578/) (2023)
- [GraCo: Granularity-Controllable Interactive Segmentation](https://mlsanity.com/paper/2405.00587/) (2024)
- [MultiverSeg: Scalable Interactive Segmentation of Biomedical Imaging Datasets with In-Context Guidance](https://mlsanity.com/paper/2412.15058/) (2024)
- [Probabilistic Attention for Interactive Segmentation](https://mlsanity.com/paper/2106.15338/) (2021)
- [Belief function-based semi-supervised learning for brain tumor segmentation](https://mlsanity.com/paper/2102.00097/) (2021)
- [Robust Interactive Semantic Segmentation of Pathology Images with Minimal User Input](https://mlsanity.com/paper/2108.13368/) (2021)
- [ScribbleGen: Generative Data Augmentation Improves Scribble-supervised Semantic Segmentation](https://mlsanity.com/paper/2311.17121/) (2023)
- [PiClick: Picking the desired mask from multiple candidates in click-based interactive segmentation](https://mlsanity.com/paper/2304.11609/) (2023)
- [Strike the Balance: On-the-Fly Uncertainty based User Interactions for Long-Term Video Object Segmentation](https://mlsanity.com/paper/2408.00169/) (2024)
- [Contour-based Interactive Segmentation](https://mlsanity.com/paper/2302.06353/) (2023)
- [Interactive Image Segmentation with Cross-Modality Vision Transformers](https://mlsanity.com/paper/2307.02280/) (2023)
- [Interactive Segmentation for Diverse Gesture Types Without Context](https://mlsanity.com/paper/2307.10518/) (2023)
- [Exploring the Interactive Guidance for Unified and Effective Image Matting](https://mlsanity.com/paper/2205.08324/) (2022)
- [RAIS: Robust and Accurate Interactive Segmentation via Continual Learning](https://mlsanity.com/paper/2210.10984/) (2022)
- [Panoptic One-Click Segmentation: Applied to Agricultural Data](https://mlsanity.com/paper/2303.08689/) (2023)
- [UAVDB: Point-Guided Masks for UAV Detection and Segmentation](https://mlsanity.com/paper/2409.06490/) (2024)
- [Contextual Guided Segmentation Framework for Semi-supervised Video Instance Segmentation](https://mlsanity.com/paper/2106.03330/) (2021)
- [Estimating Appearance Models for Image Segmentation via Tensor Factorization](https://mlsanity.com/paper/2208.07853/) (2022)
- [Variance-insensitive and Target-preserving Mask Refinement for Interactive Image Segmentation](https://mlsanity.com/paper/2312.14387/) (2023)
- [RefCut: Interactive Segmentation with Reference Guidance](https://mlsanity.com/paper/2503.17820/) (2025)

## Abstract (arXiv)

Most previous bounding-box-based segmentation methods assume the bounding box tightly covers the object of interest. However it is common that a rectangle input could be too large or too small. In this paper, we propose a novel segmentation approach that uses a rectangle as a soft constraint by transforming it into an Euclidean distance map. A convolutional encoder-decoder network is trained end-to-end by concatenating images with these distance maps as inputs and predicting the object masks as outputs. Our approach gets accurate segmentation results given sloppy rectangles while being general for both interactive segmentation and instance segmentation. We show our network extends to curve-based input without retraining. We further apply our network to instance-level semantic segmentation and resolve any overlap using a conditional random field. Experiments on benchmark datasets demonstrate the effectiveness of the proposed approaches.