SphereFlow: 6 DoF Scene Flow from RGB-D Pairs
By Michael Hornacek, Andrew William Fitzgibbon, Carsten Rother. 2014
94 citations recorded by the source corpus.
Subfields: Aerospace Engineering, 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 Aerospace Engineering
- Stefan Roth
- Andreas Geiger
- Konrad Schindler
- Rahul Sukthankar
- Moritz Menze
- Katerina Fragkiadaki
- Cordelia Schmid
- Christoph Vogel
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Wanqing Li
- Jitendra Malik
- Cordelia Schmid
- Andreas Geiger
- Xiaogang Wang
- Andrew Zisserman
- Dacheng Tao
Citations in the corpus
- Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks (2017, methodology): “In contrast to optical flow which provides the projection of the scene motion onto the image plane, scene flow [41, 6, 26, 8, 11, 37, 32] estimates the actual 3D motion field.”
- SfM-Net: Learning of Structure and Motion from Video (2017, methodology): “Similarly, direct meth-ods for visual SLAM having RGB [26] or RGBD [17] video as input, perform dense pixel matching from frame to frame while estimating a camera trajectory and depth of the pixels in the scene with impressive 3D point cloud reconstructions.”
- FlowNet3D: Learning Scene Flow in 3D Point Clouds (2018, unknown): “With the recent advent of commodity depth sensors, it has become feasible to estimate scene flow from monocular RGB-D images [9], by generalizing variational 2D flow algorithms to 3D [10, 14] and exploiting more geometric cues provided by the depth channel [21, 11, 23].”
- 3D Scene Flow Estimation with a Piecewise Rigid Scene Model (2015, background): “3D rigid body motions are further exploited in the context of scene flow estimation from RGB-D data by Hornacek et al. (2014).”
- Object scene flow for autonomous vehicles (2015, methodology): “As a representative for RGB-D based algorithms we show the results of Hornacek’s Sphere Flow [17] which have been provided to us by the authors.”
- A primal-dual framework for real-time dense RGB-D scene flow (2015, unknown): “Also for RGB-D images, SphereFlow [17] exploits the availability of depth data by seeking correspondences not in the image plane but in spheres of the 3D space, which is demonstrated to be advantageous to handle occlusion and large displacements.”