SceneNN: A Scene Meshes Dataset with aNNotations

Hua, Binh-Son; Pham, Quang-Hieu; Nguyen, Duc Thanh; Tran, Minh-Khoi; Yu, Lap-Fai; Yeung, Sai-Kit

doi:10.1109/3dv.2016.18

Cited by 273 publications

(156 citation statements)

References 38 publications

Supporting

Mentioning

156

Contrasting

Order By: Relevance

“…To compare against previous work in [5], we evaluate the 3D segmentation accuracy of the proposed dense object-level semantic mapping framework on real-world indoor scans from the SceneNN [8] dataset, improving over the baseline for most of the evaluated scenes. A sample inventory of object models discovered in these scenes is shown to contain recognized, semantically annotated elements, as well as newly discovered, previously unseen objects.…”

Section: Methodsmentioning

confidence: 99%

“…Note that different colors in Figure (a) and Figure (b) represent the different instances, and that a same instance in the prediction and ground truth is not necessarily of the same color. Progressive mapping of sequence 231 from the SceneNN [8] dataset is shown in the accompanying video available at http://youtu.be/Jvl42VJmYxg.…”

Section: Introductionmentioning

confidence: 99%

“…TO THE 3D SEMANTIC INSTANCE-SEGMENTATION APPROACH FROM PHAM et al[5]. PER-CLASS AP IS EVALUATED USING AN IOU THRESHOLD OF 0.5 FOR EACH OF THE 10 EVALUATED SEQUENCES FROM THE SCENENN[8] DATASET. THE CLASS-AVERAGED MAP VALUE IS COMPARED TO THE RESULTS PRESENTED IN[5].THE PROPOSED APPROACH IMPROVES OVER THE BASELINE FOR 7 OF THE 10 SEQUENCES EVALUATED, HOWEVER IT IS WORTH NOTING THAT THE REPORTED MAP VALUES ARE EVALUATED ON A SMALLER SET OF CLASSES COMPARED TO THE ONES FROM[5].…”

mentioning

confidence: 99%

See 2 more Smart Citations

Volumetric Instance-Aware Semantic Mapping and 3D Object Discovery

Grinvald

Furrer

Novković

et al. 2019

IEEE Robot. Autom. Lett.

218

168

View full text Add to dashboard Cite

To autonomously navigate and plan interactions in real-world environments, robots require the ability to robustly perceive and map complex, unstructured surrounding scenes. Besides building an internal representation of the observed scene geometry, the key insight toward a truly functional understanding of the environment is the usage of higher-level entities during mapping, such as individual object instances. This work presents an approach to incrementally build volumetric objectcentric maps during online scanning with a localized RGB-D camera. First, a per-frame segmentation scheme combines an unsupervised geometric approach with instance-aware semantic predictions to detect both recognized scene elements as well as previously unseen objects. Next, a data association step tracks the predicted instances across the different frames. Finally, a map integration strategy fuses information about their 3D shape, location, and, if available, semantic class into a global volume. Evaluation on a publicly available dataset shows that the proposed approach for building instance-level semantic maps is competitive with state-of-the-art methods, while additionally able to discover objects of unseen categories. The system is further evaluated within a real-world robotic mapping setup, for which qualitative results highlight the online nature of the method. Code is available at https://github.com/ethz-asl/voxblox-plusplus.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Volumetric Instance-Aware Semantic Mapping and 3D Object Discovery

Grinvald

Furrer

Novković

et al. 2019

IEEE Robot. Autom. Lett.

218

168

View full text Add to dashboard Cite

show abstract

“…We do strong supervision of the descriptor network on datasets with ground truth poses, i.e., SceneNN [13] and "3D reconstruction dataset" [38]. The loss function for strong supervision defined on a pair of overlapping point clouds X and X with ground truth poses G ∈ SE(3) and G ∈ SE(3) is given by:…”

Section: D2 Strong Supervisionmentioning

confidence: 99%

USIP: Unsupervised Stable Interest Point Detection From 3D Point Clouds

Lee

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

180

124

View full text Add to dashboard Cite

In this paper, we propose the USIP detector: an Unsupervised Stable Interest Point detector that can detect highly repeatable and accurately localized keypoints from 3D point clouds under arbitrary transformations without the need for any ground truth training data. Our USIP detector consists of a feature proposal network that learns stable keypoints from input 3D point clouds and their respective transformed pairs from randomly generated transformations. We provide degeneracy analysis of our USIP detector and suggest solutions to prevent it. We encourage high repeatability and accurate localization of the keypoints with a probabilistic chamfer loss that minimizes the distances between the detected keypoints from the training point cloud pairs. Extensive experimental results of repeatability tests on several simulated and real-world 3D point cloud datasets from Lidar, RGB-D and CAD models show that our USIP detector significantly outperforms existing hand-crafted and deep learning-based 3D keypoint detectors. Our code is available at the project website. 1 * now at nuTonomy: an APTIV company.

show abstract

“…To evaluate our system, we perform experiments on sequence 66 of the SceneNN dataset [34], where multiple identical objects are present, shown in Fig. 5, and indoor datasets collected with a Tango phone, and released with this paper 2 , see Fig.…”

Section: Methodsmentioning

confidence: 99%

Incremental Object Database: Building 3D Models from Multiple Partial Observations

Furrer

Novković

Gawel

et al. 2018

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Collecting 3D object datasets involves a large amount of manual work and is time consuming. Getting complete models of objects either requires a 3D scanner that covers all the surfaces of an object or one needs to rotate it to completely observe it. We present a system that incrementally builds a database of objects as a mobile agent traverses a scene. Our approach requires no prior knowledge of the shapes present in the scene. Object-like segments are extracted from a global segmentation map, which is built online using the input of segmented RGB-D images. These segments are stored in a database, matched among each other, and merged with other previously observed instances. This allows us to create and improve object models on the fly and to use these merged models to reconstruct also unobserved parts of the scene. The database contains each (potentially merged) object model only once, together with a set of poses where it was observed. We evaluate our pipeline with one public dataset, and on a newly created Google Tango dataset containing four indoor scenes with some of the objects appearing multiple times, both within and across scenes.

show abstract

SceneNN: A Scene Meshes Dataset with aNNotations

Cited by 273 publications

References 38 publications

Volumetric Instance-Aware Semantic Mapping and 3D Object Discovery

Volumetric Instance-Aware Semantic Mapping and 3D Object Discovery

USIP: Unsupervised Stable Interest Point Detection From 3D Point Clouds

Incremental Object Database: Building 3D Models from Multiple Partial Observations

Contact Info

Product

Resources

About