Select Language



SUN RGB-D:一个 RGB-D 解场景理解任务训练数据集

SUN RGB-D:一个 RGB-D 解场景理解任务训练数据集

434 浏览
0 喜欢
0 次下载
0 条讨论
Image Search,Deep Learning Classification

Although RGB-D sensors have enabled major breakthroughsfor several vision tasks, such as 3D reconstruction,we haven not......

数据结构 ? 6.6G

    Data Structure ?

    * 以上分析是由系统提取分析形成的结果,具体实际数据为准。

    Although RGB-D sensors have enabled major breakthroughs for several vision tasks, such as 3D reconstruction, we haven not achieved a similar performance jump for high-level scene understanding. Perhaps one of the main reasons for this is the lack of a benchmark of reasonable size with 3D annotations for training and 3D metrics for evaluation. In this paper, we present an RGB-D benchmark suite for the goal of advancing the state-of-the-art in all major scene understanding tasks. Our dataset is captured by four different sensors and contains 10,000 RGB-D images, at a similar scale as PASCAL VOC. The whole dataset is densely annotated and includes 146,617 2D polygons and 58,657 3D bounding boxes with accurate object orientations, as well as a 3D room layout and category for scenes. This dataset enables us to train data-hungry algorithms for scene-understanding tasks, evaluate them using direct and meaningful 3D metrics, avoid overfitting to a small testing set, and study cross-sensor bias.


    SUNRGB-D 3D Object Detection Challenge (2017): data and delevopment  toolkit is now available here .


    • S. Song, S. Lichtenberg, and J. Xiao.
      SUN RGB-D: A RGB-D Scene Understanding Benchmark Suite
      Proceedings of 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR2015)
      Oral Presentation

    Data and Annotation

    • SUNRGBD V1 : This file contains the 10335 RGBD images of SUNRGBD V1.

      The dataset contains RGB-D images from NYU depth v2 [1], Berkeley B3DO [2], and SUN3D [3]. Besides this paper, you are required to also cite the following papers if you use this dataset.

      [1] N. Silberman, D. Hoiem, P. Kohli, R. Fergus. Indoor segmentation and support inference from rgbd images. In ECCV, 2012.

      [2] A. Janoch, S. Karayev, Y. Jia, J. T. Barron, M. Fritz, K. Saenko, and T. Darrell. A category-level 3-d object dataset: Putting the kinect to work. In ICCV Workshop on Consumer Depth Cameras for Computer Vision, 2011.

      [3] J. Xiao, A. Owens, and A. Torralba. SUN3D: A database of big spaces reconstructed using SfM and object labels. In ICCV, 2013

    • SUNRGBDtoolbox : This file contains annotation and Matlab code to load and visualize the data. Here is the README.txt


    • Details about updates see:

    • UPDATE.txt

    • SUNRGBDmeta2DBB_v2.mat : Updated 2D bounding box.

    • SUNRGBDmeta3DBB_v2.mat : Updated 3D bounding box.


    • (15.1 MB)

    • (269 KB)

    • (274 KB)  (contains code for "Manhattan Box" and "Convex Hull" methods.)


    • deep_features.mat (230.1 MB): Places-CNN [4] features on depth and color images.


    • Oral Presentation Slides

    • Poster

    Other Materials

    • supp.pdf: This file contains more results and detials about our annotation tool.


    This work is supported by gift funds from Intel Corporation. We thank Thomas Funkhouser, Jitendra Malik, Alexi A. Efros and Szymon Rusinkiewicz for valuable discussion. We also thank Linguang Zhang, Fisher Yu, Yinda Zhang, Luna Song, Pingmei Xu and Guoxuan Zhang for capturing and labeling.


    [4] B. Zhou, A. Lapedriza, J. Xiao, A. Torralba, and A. Oliva Learning Deep Features for Scene Recognition using Places Database Advances in Neural Information Processing Systems 27 (NIPS2014)




    • 分享你的想法


    所需积分:20 去赚积分?
    • 434浏览
    • 0下载
    • 0点赞
    • 收藏
    • 分享