Object detection and classification from large‐scale cluttered indoor scans
Explore this paper's citation graph
Summary
A trivially parallelizable preprocessing step, which compresses a point cloud into a collection of nearly‐planar patches related by geometric transformations, enables us to robustly filter out noise and greatly reduces the computational cost and memory requirements of the method.
- Type
- article
- Published
- 2014-05-01
- Cited by
- 115
- References
- 38
- OpenAlex
- https://openalex.org/W1509835260
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:13498599
Keywords
Point cloud, Computer science, Artificial intelligence, Computer vision, Segmentation
References
- Segmentation and Unsupervised Part-based Discovery of Repetitive Objects
- Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration
- Factored Facade Acquisition using Symmetric Line Arrangements
- Fast and Robust Normal Estimation for Point Clouds with Sharp Features
- Acquiring 3D indoor environments with variability and repetition
- Unsupervised discovery of repetitive objects
- Min-cut based segmentation of point clouds
- Scalable Symmetry Detection for Urban Scenes
- Surface Reconstruction through Point Set Structuring
- Symmetry Detection Using Feature Lines
- Learning part-based templates from large collections of 3D shapes
- An interactive approach to semantic modeling of indoor scenes with an RGBD camera
- Object discovery in 3D scenes via shape analysis
- GlobFit: consistently fitting primitives by discovering global relations
- Partial and approximate symmetry detection for 3D geometry
- 4-points congruent sets for robust pairwise surface registration
- Real-time 3D reconstruction at scale using voxel hashing
- Detection-based object labeling in 3D scenes
- Symmetry factored embedding and distance
- O-snap
Cited by
- Scene Segmentation and Understanding for Context-Free Point Clouds
- Data‐Driven Shape Analysis and Processing
- 3D all the way: Semantic segmentation of urban scenes from start to end in 3D
- SUN RGB-D: A RGB-D scene understanding benchmark suite
- Database‐Assisted Object Retrieval for Real‐Time 3D Reconstruction
- Autoscanning for coupled scene reconstruction and proactive object analysis
- Imagining the unseen
- Fast, Automated, Scalable Generation of Textured 3D Models of Indoor Environments
- RAPter
- Activity-centric scene synthesis for functional 3D scene modeling
- Automatic room detection and reconstruction in cluttered indoor environments with complex room layouts
- Approximate 3D Partial Symmetry Detection Using Co-occurrence Analysis
- Online Structure Analysis for Real-Time Indoor Scene Reconstruction
- Automatic Indoor 3D Surface Reconstruction with Segmented Building and Object Elements
- Data-driven contextual modeling for 3D scene understanding
- Unsupervised learning of spatial-temporal models of objects in a long-term autonomy scenario
- 3D Modeling of Interior Building Environments and Objects from Noisy Sensor Suites
- Localize Me Anywhere, Anytime: A Multi-task Point-Retrieval Approach
- Cluttered indoor scene modeling via functional part-guided graph matching
- Geometric modeling of indoor scenes from acquired point data. (Modélisation géométrique de scènes intérieures à partir de nuage de points)
Related papers
- Embedding as a modeling problem
- Discussion on the Application of Visualization Technology in Modeling and Simulation
- Visualization and New Product Evaluation: the Role of Memory- and Imagination-Focused Visualization
- Views on Visualization
- Selecting Visualization Web Services Based on Visualization Characteristics
- HENSON: a visualization framework for genetic algorithm users
- Denoising of 3D Point Clouds Constructed from Light Fields
- Characteristic Analysis of Data Preprocessing for 3D Point Cloud Classification Based on a Deep Neural Network: PointNet
- Research on Preprocessing Techniques of 3D Laser Scanning Data