3D all the way: Semantic segmentation of urban scenes from start to end in 3D

By Andelo Martinovic, Jan Knopp, Hayko Riemenschneider, Luc Van Gool. 2015

145 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Environmental Engineering

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

In Environmental Engineering

Citations in the corpus

OctNet: Learning Deep 3D Representations at High Resolutions (2016, neutral): “[28] - 52.”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, background): “cade modeling approaches that treat facades as planar surfaces, Martinović et al. (2015) propose an approach for facade modeling which operates directly in 3D.”
Tangent Convolutions for Dense Prediction in 3D (2018, background): “Such approaches can also be combined with high-level architectural rules [33].”
Deep Projective 3D Semantic Segmentation (2017, background): “Popular alternatives include features based on the 3D structure tensor [7,26,11,1], histogram-based descriptors [7,16,11] such as Spin Images [10] and SHOT [21], and simple color features [26,16,11].”
STFCN: Spatio-Temporal FCN for Semantic Video Segmentation (2016, methodology): “Pixel color features are features used in almost every semantic segmentation system [12,23,29,30,33].”
Efficient 2D and 3D Facade Segmentation Using Auto-Context (2016, unknown): “Three tasks are proposed on this dataset in [14, 15] (http://varcity.eu/3dchallenge/).”
4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks (2019, unknown): “4 RF+3D CRF [18] 56.”
SEGCloud: Semantic Segmentation of 3D Point Clouds (2017, methodology): “A common paradigm in 3D semantic segmentation combines a classifier stage and a Conditional Random Field to impose smoothness and consistency [68, 69, 45, 66, 69].”
KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D (2021, background): “In the context of street view image segmentation, [14], [63], [65], [67], [69], [106] exploit the interaction between image pixels and 3D points to improve classiﬁcation performance or efﬁciency.”
Large-Scale Point Cloud Semantic Segmentation with Superpoint Graphs (2017, methodology): “The solution is then spatially regularized using graphical models [37, 24, 34, 44, 21, 2, 38, 35, 49] or structured optimization [27].”
Perception, Planning, Control, and Coordination for Autonomous Vehicles (2017, methodology): “In [62], the author implemented the Random Forest classifier to classify each point into one semantic class.”
Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer (2015, background): “While our label transfer approach does not assume geolocalization, geospatial information3 can facilitate the 3D annotation task.”
An improved LOD specification for 3D building models (2016, background): “…et al., 2015; Isikdag and Zlatanova, 2009; de Laat and van Berlo, 2011) and CAD (Lewis and Séquin, 1998; Huang et al., 2008), from architectural plans (Yin et al., 2009), ground imagery (Xiao et al., 2009), and with procedural modelling (Goetz, 2013; Smelik et al., 2014; Martinović et al., 2015).”
LiDAR-Video Driving Dataset: Learning Driving Policies Effectively (2018, methodology): “[2, 6, 8, 18] attempt to perform 3D object detection or segmentation leveraging LiDAR information.”