# LevelSet R-CNN: A Deep Variational Method for Instance Segmentation Source: [LevelSet R-CNN: A Deep Variational Method for Instance Segmentation]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:28:00.017Z Authors: Namdar Homayounfar, Yuwen Xiong, Justin Liang, Wei-Chiu Ma, Raquel Urtasun Published: 2020-07-30T17:52:18.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Instance Segmentation on COCO (val)](): Instance Segmentation; COCO (val); APmk: 34.3. ## Original sources and implementation [Original paper]() [PDF]()