3D Scene Understanding by Voxel-CRF

By Byung-soo Kim, Pushmeet Kohli, Silvio Savarese. 2013

144 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

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

Citations in the corpus

ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes (2017, methodology): “We use these tasks to demonstrate that Scan-Net enables the use of deep learning methods for 3D scene understanding tasks with supervised training, and compare performance to that using data from other existing datasets.”
OctNetFusion: Learning Depth Fusion from Data (2017, methodology): “Shape completion from a single RGB-D image has been tackled in [14, 23, 45, 56].”
Semantic Scene Completion from a Single Depth Image (2016, methodology): “[12] train a Voxel-CRF model from labeled floor plans to optimize the semantic labeling and reconstruction for indoor scenes.”
Discrete optimization of ray potentials for semantic 3D reconstruction (2015, methodology): “We propose to formulate an optimization problem which measures the data fidelity directly in image space while still having all the benefits of a volumetric representation.”
Three-Dimensional Object Detection and Layout Prediction Using Clouds of Oriented Gradients (2016, background): “A wide range of semantic 3D scene models have been developed, including approaches based on low-level voxel representations [20].”
Learning Where to Classify in Multi-view Semantic Segmentation (2014, background): “Recently, [33, 34] combined the creation of geometry with the semantic labelling implicitly evaluating all data redundantly.”
Dense Semantic 3D Reconstruction (2017, background): “Also [17] was published shortly after the earlier version of our work.”
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].”
Multi-Label Semantic 3D Reconstruction Using Voxel Blocks (2016, background): “While [10] densely labels the volume into semantic classes, [13] only labels the surface voxels into semantic classes.”
FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds (2017, background): “Applications of learning on point clouds include shape completion and recognition [54], unmanned autonomous vehicles [34], 3D object detection, recognition and classification [9, 31, 38, 39, 45, 46, 50], contour detection [20], layout inference [16], scene labeling [29], category discovery [57], poi”
Sliding Shapes for 3D Object Detection in Depth Images (2014, methodology): “Semantic segmentation: A popular way of formulating object recognition in 3D is to predict the semantic label for each region of a depth map or 3D mesh [37, 38, 11, 10, 39–44].”
SEGCloud: Semantic Segmentation of 3D Point Clouds (2017, background): “…in 3D space, which is useful for ﬁne-grained tasks such as object manipulation, detailed scene modeling, etc. Semantic segmentation of 3D point sets or point clouds has been addressed through a variety of methods leveraging the representational power of graphical models [36, 44, 3, 48, 30, 35].”
FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation (2017, background): “Applications of learning on point clouds include shape completion and recognition [57], unmanned autonomous vehicles [36], 3D object detection, recognition and classification [9, 33, 40, 41, 48, 49, 53], contour detection [21], layout inference [18], scene labeling [31], category discovery [60], poi”
3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions (2019, background): “tion [4, 35], feature extraction [24], contour detection [15], classification [29, 34], scene understanding [37, 44], and part semantic segmentation [22]).”
A Robust 3D-2D Interactive Tool for Scene Segmentation and Annotation (2016, methodology): “The spatial relationship between objects was modeled by a conditional random field (CRF) in [25], [26] and directed graph in [27].”
3D all the way: Semantic segmentation of urban scenes from start to end in 3D (2015, background): “Since then, recent works show the advantage of combining 3D and 2D for classification [42, 21, 19, 38, 56] or place recognition [37] using LIDAR, 3D CAD or Kinect models.”