Name
Abstract | ||
|---|---|---|
This paper presents a novel method for dense 3D reconstruction of man-made environments. Such environments suffer from texture less and non-Lambertian surfaces, where conventional, feature-Based 3D reconstruction pipelines fail to obtain good feature matches. To compensate this lack of feature matches, we exploit the semantic information available in 2D images to estimate both a corresponding 3D position and a 3D surface normal for each pixel. A semantic classifier is therefore applied on a single segmented image in order to get a likelihood for a segment providing one of the surface normals within a discrete set of them. To improve the accuracy of this labeling step, we exploit multiple segmentation methods. The global best surface normal configuration over all pixels of an image is then obtained by using a Markov Random Field. In the last step, the 3D model of a single 2D input image is reconstructed by combining the semantic surface normal estimation with the sparse point cloud coming from feature Based matching. It is shown experimentally, that our proposed method clearly outperforms state-of-the-art dense 3D reconstruction pipelines and surface layout estimation approaches. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/3DV.2013.64 | Seattle, WA |
Keywords | Field | DocType |
good feature,surface normal,global best surface,combining multiple segmentation methods,normal estimation,input image,surface layout estimation approach,non-lambertian surface,normal configuration,reconstruction pipeline,sparse point cloud densification,semantic surface,image classification,markov processes,image reconstruction,random processes,image segmentation,feature extraction | Computer vision,Scale-space segmentation,Feature detection (computer vision),Pattern recognition,Computer science,Range segmentation,Image texture,Segmentation-based object categorization,Feature extraction,Image segmentation,Artificial intelligence,Point cloud | Conference |
Citations | PageRank | References |
1 | 0.35 | 19 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Michael Hodlmoser | 1 | 18 | 2.81 |
| Branislav Micusik | 2 | 30 | 3.98 |
| Martin Kampel | 3 | 12 | 1.85 |