A search-classify approach for cluttered indoor scene understanding

By Liangliang Nan, Ke Xie, Andrei Sharf. 2012

284 citations recorded by the source corpus.

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

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

In Model Architectures

Citations in the corpus

Multiview Compressive Coding for 3D Reconstruction (2023, methodology): “For scenes, techniques include plane fitting [38], 3D model fitting and retrieval [14, 39] or leverage symmetries [27] and predict 3D semantics [3, 13, 58].”
Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis (2016, methodology): “Another idea is to ﬁnd identical CAD models in a shape database for a given partial input shape and align it with the scan [24, 33, 16, 21, 35].”
Semantic Scene Completion from a Single Depth Image (2016, background): “One possible approach to obtain the complete geometry and semantic labels for a scene is to retrieve and fit instance-level 3D mesh models to the observed depth map [7, 30, 4, 16, 23, 17, 14].”
3 D ShapeNets : A Deep Representation for Volumetric Shape Modeling (2015, background): “While there is some good research on shape synthesis [7] [16] and shape reconstruction [27] [22], they are mostly limited to part-based assembly and suffer from establishing bad local correspondences.”
Scan2CAD: Learning CAD Model Alignment in RGB-D Scans (2018, methodology): “[28] use a random decision forest to classify objects on over-segmented input geometry from high-quality scans.”
Learning 3D Shape Completion from Laser Scan Data with Weak Supervision (2018, unknown): “In [3, 10, 13, 14, 21, 30, 32] shape”
Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement (2022, methodology): “3D Object Detection: Early 3D object detection methods mainly include template-based methods [16, 18, 23] and sliding-window methods [37, 38].”
Sliding Shapes for 3D Object Detection in Depth Images (2014, background): “Since our generic object detector does not reply on any assumption about the background or requires a dominant supporting plane [15, 16], and its single-view nature doesn’t require a (semi-)complete scan of an object [17], it can be used as a basic building block for general scene understanding task”
Learning part-based templates from large collections of 3D shapes (2013, methodology): “…for data-driven solutions to common geometry processing problems, including surface reconstruction [Kim et al. 2012b], model completion [Shen et al. 2012], model-based object recognition [Shapira et al. 2010; Nan et al. 2012], shape synthesis [Kalogerakis et al. 2012; Zheng et al. 2013], etc.”
State of the Art in Surface Reconstruction from Point Clouds (2014, unknown): “This is addressed in [NXS12] where upon ﬁnding a certain semantic class for a segmented object in the point cloud, every model is non-rigidly deformed via localized scale deformations.”
Scene Understanding by Reasoning Stability and Safety (2015, background): “…many semantic labeling methods for 3D point clouds play an important role in robotics: Koppula et al. (2011); Anand et al. (2012); Wu et al. (2014), etc; in graphics: e.g., Nan et al. (2012); Shao et al. (2012, 2014); Savva et al. (2014), etc; in 3D shape recognition: Karpathy et al. (2013), etc.”
SceneGrok (2014, methodology): “More sophisticated scene parsing methods (e.g., [Nan et al. 2012]) may be useful for improved segmentation of the input scenes.”
Data-driven structural priors for shape completion (2015, methodology): “Other approaches take advantage of efficient featurebased descriptors and simply use the most similar object to complete the 3D scan [Nan et al. 2012; Kim et al. 2013b; Li et al. 2015].”
3D Object Reconstruction from a Single Depth View with Adversarial Learning (2017, methodology): “Given a partial shape input, [25] [29] [36] [45] [47] try to retrieve an identical or most likely CAD model and align it with the partial scan.”