Real-Time Direct Dense Matching on Fisheye Images Using Plane-Sweeping Stereo
By Christian Häne, Lionel Heng, Gim Hee Lee, Alexey Sizov, Marc Pollefeys. 2014
93 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
- Andreas Geiger
- Luc Van Gool
- Jitendra Malik
- Marc Pollefeys
- Ming-Hsuan Yang
- Xiaogang Wang
- Dacheng Tao
- Bernt Schiele
Citations in the corpus
- RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials (2018, methodology): “We follow [11] and compute the max score among all pairs of patch combinations, which allows some robustness to occlusions.”
- Learning a Multi-View Stereo Machine (2017, methodology): “We use the publicly available implementation of [19] for the PS algorithm and use 5x5 zero mean normalized cross correlation as matching windows with 300 depth planes.”
- Dense Semantic 3D Reconstruction (2017, background): “sweep stereo matching implementation [11], for each of the images with zero mean normalized cross correlation (ZNCC) matching costs.”
- Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, methodology): “The project supported many works on different problems such as calibration Heng et al. (2013, 2015), stereo Häne et al. (2014), reconstruction Haene et al. (2012, 2013, 2014), SLAM Grimmett et al. (2015) and free space detection Häne et al. (2015).”
- Learned Multi-patch Similarity (2017, methodology): “One exhaustively tests for all possible depths, often by “sweeping” a fronto-parallel plane through the 3D object space along the depth axis [4] or in multiple directions [10] to sample different depth values efficiently.”
- Multi-Label Semantic 3D Reconstruction Using Voxel Blocks (2016, methodology): “We obtained the camera poses using a publicly available structure from motion pipeline [29], and the depth maps are obtained using the publicly available plane sweep stereo matching implementation [9] with zero mean normalized cross correlation and subsequent semiglobal matching on the cost volume [”