paper-with-me

Papers

Sparse Layered Graphs for Multi-Object Segmentation

2020-06-01 · CVPR 2020 6 · Niels Jeppesen, Anders N. Christensen, Vedrana A. Dahl, Anders B. Dahl

We introduce the novel concept of a Sparse Layered Graph (SLG) for s-t graph cut segmentation of image data. The concept is based on the widely used Ishikawa layered technique for multi-object segmentation, which allows explicit object interactions, such as containment and exclusion with margins. However, the spatial complexity of the Ishikawa technique limits its use for many segmentation problems. To solve this issue, we formulate a general method for adding containment and exclusion interaction constraints to layered graphs. Given some prior knowledge, we can create a SLG, which is often orders of magnitude smaller than traditional Ishikawa graphs, with identical segmentation results. This allows us to solve many problems that could previously not be solved using general graph cut algorithms. We then propose three algorithms for further reducing the spatial complexity of SLGs, by using ordered multi-column graphs. In our experiments, we show that SLGs, and in particular ordered multi-column SLGs, can produce high-quality segmentation results using extremely simple data terms. We also show the scalability of ordered multi-column SLGs, by segmenting a high-resolution volume with several hundred interacting objects.

📄 PDF Abstract BibTeX

Code (1)

Skielex/slgbuilder 공식 구현

Tasks

ObjectSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Extending Layered Models to 3D Motion

2018-09-01 · ECCV 2018 9 · Dong Lao, Ganesh Sundaramoorthi

We consider the problem of inferring a layered representa-tion, its depth ordering and motion segmentation from a video in whichobjects may undergo 3D non-planar motion relative to the camera. Wegeneralize layered infere…

Motion SegmentationObjectSegmentationUnsupervised Video Object Segmentation

GraphSeg: Segmented 3D Representations via Graph Edge Addition and Contraction

2025-04-04 · Haozhan Tang, Tianyi Zhang, Oliver Kroemer, Matthew Johnson-Roberson 외

Robots operating in unstructured environments often require accurate and consistent object-level representations. This typically requires segmenting individual objects from the robot's surroundings. While recent large mo…

Image SegmentationSegmentationSemantic Segmentation

Learning Foreground-Background Segmentation from Improved Layered GANs

2021-04-01 · Yu Yang, Hakan Bilen, Qiran Zou, Wing Yin Cheung 외

Deep learning approaches heavily rely on high-quality human supervision which is nonetheless expensive, time-consuming, and error-prone, especially for image segmentation task. In this paper, we propose a method to autom…

Generative Adversarial NetworkImage SegmentationSegmentationSemantic Segmentation+1

A Fully-Connected Layered Model of Foreground and Background Flow

2013-06-01 · CVPR 2013 6 · Deqing Sun, Jonas Wulff, Erik B. Sudderth, Hanspeter Pfister 외

Layered models allow scene segmentation and motion estimation to be formulated together and to inform one another. Traditional layered motion methods, however, employ fairly weak models of scene structure, relying on loc…

Motion EstimationScene Segmentation

Defect Detection by MIMO Wireless Sensing based on Weighted Low-Rank plus Sparse Recovery

2020-10-31 · Udaya S. K. P. Miriya Thanthrige, Ali Kariminezhad, Peter Jung, Aydin Sezgin

We present a compressive sensing based defect detection by multiple input multiple output (MIMO) wireless radar. Here, defects are inside a layered material structure, therefore, due to reflections from the surface of th…

Compressive SensingDefect Detection