Large-Scale Semantic 3D Reconstruction: An Adaptive Multi-resolution Model for Multi-class Volumetric Labeling

By M. Blaha, Christoph Vogel, Audrey Richard, Jan Dirk Wegner, Thomas Pock, Konrad Schindler. 2016

101 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Graphics and Computer-Aided Design, 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 Aerospace Engineering

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

In 3D Vision & Pose

Citations in the corpus

3D Instance Segmentation of MVS Buildings (2021, methodology): “The existing multi-view semantic segmentation framework projects the 2D semantic labels back to the 3D model with the highest probability [44], [45].”
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, background): “Noise reduction can be achieved using variational techniques which integrate local smoothness assumptions [2, 19, 55] into the formulation.”
Semantic Scene Completion from a Single Depth Image (2016, methodology): “ voxels by physical reasoning. Kim et al. [12] train a Voxel-CRF model from labeled ﬂoor plans to optimize the semantic labeling and reconstruction for indoor scenes. Hane et al. [9] and Blaha et al. [1] use joint optimization for multi-view reconstruction and segmentation for outdoor scenes. Howeve”
GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose (2018, background): “Advances have been achieved recently in robust and discriminative feature descriptors [2, 39], more efficient tracking systems [55], and better exploitation of semantic level information [4], etc.”
Multi-Label Semantic 3D Reconstruction Using Voxel Blocks (2016, methodology): “Another line of research is to combine our block approach with the method of [1] to allow for spatially larger scenes with many labels.”
Deep learning in remote sensing: a review (2017, methodology): “” Figure 14 shows an image of a semantic 3-D reconstruction produced by the method described in [172].”
Dense Semantic 3D Reconstruction (2017, methodology): “This has already been done as a follow up of our work in [2].”
Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation (2022, methodology): “Multi-view reconstruction and segmentation: Incorporating semantics into SLAM and SfM systems has a long history [2, 19, 27, 50].”