Learning Where to Classify in Multi-view Semantic Segmentation

By Hayko Riemenschneider, András Bódis-Szomorú, Julien Weissenberg, Luc Van Gool. 2014

120 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, 3D Vision & Pose

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

In 3D Vision & Pose

Citations in the corpus

The Cityscapes Dataset for Semantic Urban Scene Understanding (2016, neutral): “DUS consists of a video sequence of 5000 images from which 500 have been annotated.”
OctNet: Learning Deep 3D Representations at High Resolutions (2016, methodology): “We use the RueMonge2014 dataset [37] that provides a colored 3D point cloud of several Haussmanian style facades, comprising ∼1 million 3D points in total.”
SEGCloud: Semantic Segmentation of 3D Point Clouds (2017, background): “Several 3D Scene datasets have been made available to the research community [56, 4, 5, 31, 59, 72, 52, 16, 24, 74].”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, background): “To increase efficiency, Riemenschneider et al. (2014) exploit the inherent redundancy in the labeling of all overlapping images used for the 3D model.”
Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer (2015, background): “For street scenes, less annotated data is available [3, 29, 30, 33, 43].”
JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds With Multi-Task Pointwise Networks and Multi-Value Conditional Random Fields (2019, background): “, random forests [14, 36, 46, 42], or deep neural networks [27, 49, 30].”
Perception, Planning, Control, and Coordination for Autonomous Vehicles (2017, methodology): “A commonly used dataset is proposed in [61], which contains a colored 3D point cloud of several Haussmanian style facades.”
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/).”
The Hessigheim 3D (H3D) Benchmark on Semantic Segmentation of High-Resolution 3D Point Clouds and Textured Meshes from UAV LiDAR and Multi-View-Stereo (2021, background): “…Mobile Laser Scanning (MLS) point clouds of typical urban scenes are often provided as stand-alone products (Roynard et al., 2018; Munoz et al., 2009; Hackel et al., 2017), the concurrent availability of LiDAR data and imagery in the form of meshes is often pursued (Riemenschneider et al., 2014).”
KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D (2021, unknown): “ing scenes have been released in the literature [8], [9], [13], [18], [25], [34], [36], [45], [52], [56], [62], [65], [70], [80], [84],”
SUM: A Benchmark Dataset of Semantic Urban Meshes (2021, background): “To the best of our knowledge, the ETHZ RueMonge 2014 [28] is the ﬁrst urban-related benchmark dataset available as surface meshes.”
3D all the way: Semantic segmentation of urban scenes from start to end in 3D (2015, methodology): “Extremely challenging subset of RueMonge2014, dubbed Sub28 in [34].”
4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks (2019, methodology): “Specifically, when we simulate Table 5: RueMonge 2014 dataset (Varcity) TASK3 [26]”
Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark (2017, background): “2Note that, besides laser scanner point clouds, it is also more efficient to classify point clouds generated from SfM pipelines directly instead of going through all individual images to then merge results (Riemenschneider et al., 2014).”
SPLATNet: Sparse Lattice Networks for Point Cloud Processing (2018, methodology): “On RueMonge2014, we conducted experiments on the tasks of 3D point cloud labeling and multi-view image labeling.”
General-Purpose Deep Point Cloud Feature Extractor (2018, background): “There are other 3D datasets, such as those used for 3D estimation in cities [59, 36, 42].”
Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline (2021, methodology): “…for using projection-based methods on various point-cloud analysis problems like segmentation (Ladick ` y et al., 2010; Tighe & Lazeb-nik, 2010; Riemenschneider et al., 2014; Qin et al., 2018; Dai & Nießner, 2018; Kalogerakis et al., 2017; Tatarchenko et al., 2018), reconstruction (Pittaluga…”