A Fully-Connected Layered Model of Foreground and Background Flow

By Deqing Sun, Jonas Wulff, Erik B. Sudderth, Hanspeter Pfister, Michael J. Black. 2013

113 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

Citations in the corpus

SegFlow: Joint Learning for Video Object Segmentation and Optical Flow (2017, unknown): “The joint problem of video segmentation and flow estimation has been studied by layered models [8, 38].”
Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks (2015, background): “The dense CRF models have found wide-spread use in various computer vision applications [43, 10, 49, 47, 46, 11].”
Video Segmentation via Object Flow (2016, methodology): “In contrast, the results from [6] are usually oversmoothed around the object boundaries, and the layered model [32] generates incomplete flows inside objects.”
Object scene flow for autonomous vehicles (2015, methodology): “Inspired by recent trends in optical flow [21, 30, 40, 41] and stereo [2,3,42], Vogel et al.”
Efficient sparse-to-dense optical flow estimation using a learned basis and layers (2015, methodology): “On Sintel it is more accurate than recent methods like MDP-Flow2 [53], EPPM [4], MLDP-OF [33], Classic+NLP [44] and the traditional layered approach, FC-2Layers-FF [46], which is a least two orders of magnitude slower.”
Layered RGBD scene flow estimation (2015, methodology): “Recent RGB layered methods [40, 41] have obtained promising results in the presence of occlusions, but are computationally expensive.”
3D Scene Flow Estimation with a Piecewise Rigid Scene Model (2015, background): “Sun et al. (2010, 2013) argue that the scene structure is more likely to persist over time than any motion pattern, hence avoid temporal smoothing at all, and instead jointly estimate the ﬂow together with a segmentation into a small number of layers while requiring the pixel-to-layer membership to…”
DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency (2018, background): “For examples, joint learning of video segmentation and optical flow through layered models [6,56] or feature sharing [9] helps improve accuracy at motion boundaries.”
Optical Flow with Semantic Segmentation and Localized Layers (2016, methodology): “[49] is that we have a semantic segmentation for the foreground and this segmentation is usually reasonably good.”
A Quantitative Analysis of Current Practices in Optical Flow Estimation and the Principles Behind Them (2013, methodology): “Severalrecent and high-ranking methods directly build on Classic+NL , such as layered models (Sun et al. 2010b, 2012, 2013), meth-ods with more advanced motion prior models (Chen et al. 2012; Jia et al. 2011), efﬁcient optimization schemes for the non-local term (Krähenbühl and Koltun 2012), and…”