# LevelSet R-CNN: A Deep Variational Method for Instance Segmentation

arXiv: https://arxiv.org/abs/2007.15629 · HTML: https://mlsanity.com/paper/2007.15629/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2020.

## Built on by (most cited first, 13 of 13)

- [Bayesian Prompt Learning for Image-Language Model Generalization](https://mlsanity.com/paper/2210.02390/) (2022)
- [Box-supervised Instance Segmentation with Level Set Evolution](https://mlsanity.com/paper/2207.09055/) (2022)
- [Topologically-Aware Deformation Fields for Single-View 3D Reconstruction](https://mlsanity.com/paper/2205.06267/) (2022)
- [MGNet: Monocular Geometric Scene Understanding for Autonomous Driving](https://mlsanity.com/paper/2206.13199/) (2022)
- [Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution](https://mlsanity.com/paper/2212.01579/) (2022)
- [VideoClick: Video Object Segmentation with a Single Click](https://mlsanity.com/paper/2101.06545/) (2021)
- [RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenes](https://mlsanity.com/paper/2104.04606/) (2021)
- [VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2511.22664/) (2025)
- [Split GCN: Effective Interactive Annotation for Segmentation of Disconnected Instance](https://mlsanity.com/paper/2112.06454/) (2021)
- [ContourRender: Detecting Arbitrary Contour Shape For Instance Segmentation In One Pass](https://mlsanity.com/paper/2106.03382/) (2021)
- [Deep Level Set for Box-supervised Instance Segmentation in Aerial Images](https://mlsanity.com/paper/2112.03451/) (2021)
- [Single Point, Full Mask: Velocity-Guided Level Set Evolution for End-to-End Amodal Segmentation](https://mlsanity.com/paper/2508.01661/) (2025)
- [TA-LSDiff:Topology-Aware Diffusion Guided by a Level Set Energy for Pancreas Segmentation](https://mlsanity.com/paper/2511.00815/) (2025)

## Abstract (arXiv)

Obtaining precise instance segmentation masks is of high importance in many modern applications such as robotic manipulation and autonomous driving. Currently, many state of the art models are based on the Mask R-CNN framework which, while very powerful, outputs masks at low resolutions which could result in imprecise boundaries. On the other hand, classic variational methods for segmentation impose desirable global and local data and geometry constraints on the masks by optimizing an energy functional. While mathematically elegant, their direct dependence on good initialization, non-robust image cues and manual setting of hyperparameters renders them unsuitable for modern applications. We propose LevelSet R-CNN, which combines the best of both worlds by obtaining powerful feature representations that are combined in an end-to-end manner with a variational segmentation framework. We demonstrate the effectiveness of our approach on COCO and Cityscapes datasets.