Name
Abstract | ||
|---|---|---|
Semantic reconstruction of a scene is important for a variety of applications such as 3D modelling, object recognition and autonomous robotic navigation. However, most object labelling methods work in the image domain and fail to capture the information present in 3D space. In this work we propose a principled way to generate object labelling in 3D. Our method builds a triangulated meshed representation of the scene from multiple depth estimates. We then define a CRF over this mesh, which is able to capture the consistency of geometric properties of the objects present in the scene. In this framework, we are able to generate object hypotheses by combining information from multiple sources: geometric properties (from the 3D mesh), and appearance properties (from images). We demonstrate the robustness of our framework in both indoor and outdoor scenes. For indoor scenes we created an augmented version of the NYU indoor scene dataset (RGBD images) with object labelled meshes for training and evaluation. For outdoor scenes, we created ground truth object labellings for the KITTY odometry dataset (stereo image sequence). We observe a significant speed-up in the inference stage by performing labelling on the mesh, and additionally achieve higher accuracies. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/CVPR.2013.269 | CVPR |
Keywords | Field | DocType |
nyu indoor scene dataset,object recognition,outdoor scenes,object labelled mesh,outdoor scene,object hypothesis,indoor scene,semantic modelling,rgbd image,kitty odometry dataset,ground truth object labellings,geometric property,3d mesh,feature extraction,image reconstruction,labeling,semantics | Iterative reconstruction,Computer vision,Polygon mesh,Pattern recognition,Computer science,Inference,Odometry,Robustness (computer science),Ground truth,Triangulation,Artificial intelligence,Cognitive neuroscience of visual object recognition | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1063-6919 |
Citations | PageRank | References |
36 | 1.00 | 26 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Julien Valentin | 1 | 163 | 11.11 |
| Sunando Sengupta | 2 | 93 | 2.93 |
| Jonathan Warrell | 3 | 494 | 18.95 |
| Ali Shahrokni | 4 | 138 | 10.21 |
| Philip H. S. Torr | 5 | 9140 | 636.18 |