Indoor Challenges

For any questions, contact nathan (dot) silberman (at) gmail (dot) com

We employ the NYU Depth V2 and Sun3D datasets to define the training data for the RMRC 2014 indoor challenges. The test data consists of newly acquired images and will be released shortly.

Semantic Segmentation

Dataset: The semantic segmentation training set consists of 1800 RGB-D images. Each pixel in each image is labeled with one of the following 23 classes: background, bathtub, bed, blinds, cabinet, ceiling, chair, counter, curtain, desk, dresser, floor, night stand, picture, pillow, refrigerator, shelves, sofa, table, television, toilet, wall, window.

Evaluation: To evaluate the segmentation accuracy, we use the Jaccard index: the mean of the per-class intersection over union scores.

Downloads:

• Training Data
• Testing Data
• Development Kit

Normals from RGB

Dataset: The Normals from RGB dataset consists of 4105 RGB and surface normal pairs.

Evaluation: To evaluate the surface normals prediction accuracy, we compute the mean angular distance between each predicted surface normal and each ground truth surface normal.

Downloads:

• Training Data, each part contains a set of images, their corresponding surface normals, and a map of pixels whose normals could not be accurately computed.
  • Part 1
  • Part 2
  • Part 3
  • Part 4
  • Part 5
  • Part 6
  • Part 7
  • Part 8
  • Part 9
  • Part 10
  • Part 11
  • Part 12
  • Part 13
  • Part 14
• Test
• Development Kit

Depth from RGB

Dataset: The depth from RGB dataset consists of 4105 RGB and Depth pairs. To deal with the inherent ambiguity in the scene scale, we have also provided the absolute height of each scene along with the RGB and Depth pairs.

Evaluation: To evaluate the depth prediction accuracy, we compute the mean absolute relative error (per pixel). A depth pixel's relative error is the difference between the predicted and ground truth absolute depth divided by ground truth depth absolute depth.

Downloads:

• Training Data
  • Part 1
  • Part 2
  • Part 3
  • Part 4
  • Part 5
  • Part 6
  • Part 7
  • Part 8
  • Part 9
  • Part 10
  • Part 11
  • Part 12
  • Part 13
  • Part 14
• Test
• Development Kit

(Taster) RGBD Instance Segmentation

Dataset: The instance segmentation dataset consists of 1449 RGB and Depth frames.

Evaluation: To evaluate the instance segmentation accuracy, we measure the coverage score for each image and compute the mean coverage score over every image.

Downloads:

• Training Data
• Testing Data
• Development Kit