Dense 3D semantic mapping of indoor scenes from RGB-D images

By Alexander Hermans, Georgios Floros, Bastian Leibe. 2014

282 citations recorded by the source corpus.

Subfields: Aerospace Engineering, 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 Aerospace Engineering

In Computer Vision and Pattern Recognition

In Environmental Engineering

Citations in the corpus

ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes (2017, background): “The goal of the task is to classify the object represented by a set of scanned points within a given bounding box.”
Meaningful maps with object-oriented semantic mapping (2016, unknown): “lem and the semantic information is not used to inform the mapping part. The semantics, however, help in eradicating dynamic objects from the map. Similar idea for indoor scenes has been presented in [5]. Kundu et al. [18] derive a CRF model over 3D space, that jointly infers the semantic category a”
3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation (2018, unknown): “ly). 14 A. Dai and M. Nieˇner bed books ceil. chair oor furn. obj. pic. sofa table tv wall wind. avg. SceneNet [36] 70.8 5.5 76.2 59.6 95.9 62.3 50.0 18.0 61.3 42.2 22.2 86.1 32.1 52.5 Hermans et al. [37] 68.4 45.4 83.4 41.9 91.5 37.1 8.6 35.8 58.5 27.7 38.4 71.8 48.0 54.3 SemanticFusion [38] (RGBD+”
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling (2015, methodology): “Another approach focusses on real-time joint reconstruction and semantic segmentation, where Random Forests are used as the classiﬁer [13].”
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation (2015, methodology): “Another approach focuses on real-time joint reconstruction and semantic segmentation, where Random Forests are used as the classifier [34].”
Incremental dense semantic stereo fusion for large-scale semantic scene reconstruction (2015, methodology): “[9] use a random forest classifier and a dense 2D CRF, transfer the resulting marginals into 3D and”
Structured Prediction of Unobserved Voxels from a Single Depth Image (2016, background): “(d) (Output) Our Voxlets algorithm predicts a plausible completion of the occluded geometry. depth images of a scene captured from multiple viewpoints, thus coping with the effects of occlusion (e.g. [45] [28] [26]).”
Fusion++: Volumetric Object-Level SLAM (2018, background): “We found that the standard multiplicative Bayesian update scheme [15, 20]:”
SemanticFusion: Dense 3D semantic mapping with convolutional neural networks (2016, methodology): “Finally, we also experiment with a CRF regularisation scheme to use the geometry of the map itself to improve the semantic predictions [7], [12].”
In-Place Scene Labelling and Understanding with Implicit Scene Representation (2021, methodology): “There have been several classical pixel-wise semantic fusion approaches [6, 13, 12] to integrate monocular CNN predictions from multiple viewpoints to reﬁne segmentation.”
Scale Space and Variational Methods in Computer Vision (2015, methodology): “[7] report that about 60 % of the neurons can be described as separable in the time-frequency domain (see Figure 2, top row), whereas the remaining neurons are either obliquely oriented (see Figure 2, second row) or contain multiple excitatory/inhibitory subfields.”
MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects (2018, methodology): “[19] implements a similar scheme, using a randomised decision forest classifier.”
3D Semantic Parsing of Large-Scale Indoor Spaces (2016, unknown): “3.2).”
Understanding RealWorld Indoor Scenes with Synthetic Data (2015, methodology): “[21] use “Decoration” and “Bookshelf ” instead of painting and books as the other two classes.”
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture (2014, methodology): “When labeling the NYUDepth RGB-D dataset, we use the ground truth depth and normals as additional input channels.”
Tangent Convolutions for Dense Prediction in 3D (2018, background): “A popular line of work exploits graphical models, including conditional random fields [38, 11, 2, 58, 19, 27, 56].”
ImVoteNet: Boosting 3D Object Detection in Point Clouds With Image Votes (2020, background): “Semantic segmentation of 3D scenes often uses both RGB and depth data [10, 27].”
JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds With Multi-Task Pointwise Networks and Multi-Value Conditional Random Fields (2019, background): “Literature has shown that the data of a 3D scene can be represented by a set of images capturing the scene at different viewpoints [14, 46, 42], in a regular grid of volumes [47, 26, 28], or simply in a 3D point cloud [33, 16, 45, 17, 24].”
SEGCloud: Semantic Segmentation of 3D Point Clouds (2017, unknown): “[29] 68.”