Dense planar SLAM

By Renato F. Salas-Moreno, Ben Glocker, Paul H. J. Kelly, Andrew J. Davison. 2014

217 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology

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

In Computer Vision and Pattern Recognition

In Geology

Citations in the corpus

RGB-D datasets using microsoft kinect or similar sensors: a survey (2016, methodology): “The related performance comparisons between TUM Benchmark dataset and ICL-NUIM dataset are shown in [22] and [75].”
Co-fusion: Real-time segmentation, tracking and fusion of multiple objects (2017, background): “Achieving higher level semantic scene descriptions by using a dense planar representation [21] or real-time 3D object recognition [22] further improved tracking performance while opening the door to virtual or even real interaction with the scene.”
Revisiting Trends in Augmented Reality Research: A Review of the 2nd Decade of ISMAR (2008–2017) (2018, methodology): “[124] proposed a method for using higher-level entities, such as planes and surface elements extracted from depth images, to build dense structures of the environment in real-time 3D SLAM systems.”
Efficient Surfel-Based SLAM using 3D Laser Range Data in Urban Environments (2018, methodology): “We employ a surfel-based map [31, 12, 24, 33], since it allows us to represent even large-scale environments and maintain dense, detailed geometric information of the point clouds at the same time (see Figure 4 for an example).”
Visual SLAM algorithms: a survey from 2010 to 2016 (2017, background): “In the literature [59], they reduce amount of data by unifying co-planar points.”
ElasticFusion: Real-time dense SLAM and light source estimation (2016, background): “This is well within the widely accepted minimum frequencies for fused dense SLAM algorithms (Chen et al., 2013; Keller et al., 2013; Salas-Moreno et al., 2014; Whelan et al., 2012), and as shown in our qualitative results, are more than adequate for real-time operation.”
ElasticFusion: Dense SLAM Without A Pose Graph (2015, background): “This is well within the widely accepted minimum frequencies for fused dense SLAM algorithms [24, 17, 2, 9], and as shown in our qualitative results more than adequate for real-time operation.”
CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAM (2018, background): “Other more general scene elements which exhibit simple regularity such as planes can be recognised and efﬁ-ciently parametrised within SLAM systems (e.g. [26, 12]).”
SemanticFusion: Dense 3D semantic mapping with convolutional neural networks (2016, unknown): “ticFusion is highly suitable for applying operations such as class-specific smoothing (as in the extreme case of planar region recognition and fitting [18]), and this will be an interesting direction.”