TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/SUN RGB-D

SUN RGB-D

ImagesInteractivePoint cloudRGB-DUnknownIntroduced 2015-01-01

The SUN RGBD dataset contains 10335 real RGB-D images of room scenes. Each RGB image has a corresponding depth and segmentation map. As many as 700 object categories are labeled. The training and testing sets contain 5285 and 5050 images, respectively.

Source: Mix and match networks: multi-domain alignment for unpaired image-to-image translation Image Source: https://rgbd.cs.princeton.edu/

Benchmarks

16k/AP@0.15 (NYU-37)16k/AP@0.15 (10 / NYU-37)16k/AP@0.15 (10 / PNet-30)16k/AP 0.52D Classification/AP@0.15 (NYU-37)2D Classification/AP@0.15 (10 / NYU-37)2D Classification/AP@0.15 (10 / PNet-30)2D Classification/AP 0.52D Object Detection/AP@0.15 (NYU-37)2D Object Detection/AP@0.15 (10 / NYU-37)2D Object Detection/AP@0.15 (10 / PNet-30)2D Object Detection/AP 0.53D/AP@0.15 (NYU-37)3D/AP@0.15 (10 / NYU-37)3D/AP@0.15 (10 / PNet-30)3D/AP 0.53D Object Detection/AP@0.15 (NYU-37)3D Object Detection/AP@0.15 (10 / NYU-37)3D Object Detection/AP@0.15 (10 / PNet-30)Object Detection/AP@0.15 (NYU-37)Object Detection/AP@0.15 (10 / NYU-37)Object Detection/AP@0.15 (10 / PNet-30)Object Detection/AP 0.5Room Layout Estimation/IoURoom Layout Estimation/Camera PitchRoom Layout Estimation/Camera Roll

Statistics

Papers
477
Benchmarks
26

Links

Homepage

Tasks

16k2D Classification2D Object Detection3D3D Object DetectionMonocular 3D Object DetectionMonocular Depth EstimationObject DetectionObject Detection In Indoor ScenesPanoptic SegmentationPanoptic Segmentation (PanopticNDT instances)Robust Semi-Supervised RGBD Semantic SegmentationRoom Layout EstimationScene Classification (unified classes)Scene RecognitionScene SegmentationSemantic Segmentation