Dense Semantic 3D Reconstruction
By Christian Häne, Christopher Zach, Andrea Cohen, Marc Pollefeys. 2017
88 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
- Abhishek Kar
- Jitendra Malik
- Christian Häne
- Gregory Hager
- Andrea Vedaldi
- Ross B. Girshick
- Saurabh Gupta
- Kristen Grauman
In Computer Vision and Pattern Recognition
- Jitendra Malik
- Abhishek Kar
- Luc Van Gool
- Christian Häne
- Andreas Geiger
- Andrea Vedaldi
- Xiaogang Wang
- Trevor Darrell
Citations in the corpus
- Learning a Multi-View Stereo Machine (2017, methodology): “onforming to global structure. Learning has been used for multi-view reconstruction in the form of shape priors for objects [2, 9, 58, 20, 27, 52], or semantic class specific surface priors for scenes [22, 17, 45]. These works use learnt shape models and either directly fit them to input images or uti”
- DeepMVS: Learning Multi-view Stereopsis (2018, unknown): “Aside from photometric consistency, other 3D cues such as lighting [39, 24], shadows [1], color [11], geometric structures [7], and semantic cues [14] have been incorporated into the MVS pipeline for improving the reconstruction accuracy.”
- Semantic Stereo for Incidental Satellite Images (2018, background): “Two of the most promising recent research directions in computational stereo are pairwise stereo matching methods using convolutional neural networks (CNNs) [2] and the incorporation of semantic labels into stereo matching and 3D reconstruction methods [3].”