Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

Datasets/Matterport3D

Matterport3D

3DRGB-DCustom (non-commercial)Introduced 2017-01-01

The Matterport3D dataset is a large RGB-D dataset for scene understanding in indoor environments. It contains 10,800 panoramic views inside 90 real building-scale scenes, constructed from 194,400 RGB-D images. Each scene is a residential building consisting of multiple rooms and floor levels, and is annotated with surface construction, camera poses, and semantic segmentation.

Source: Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention

Benchmarks

10-shot image generation/Test mIoU 10-shot image generation/Validation mIoU 3D/Abs Rel 3D/Delta < 1.25 3D/Delta < 1.25^2 3D/Delta < 1.25^3 3D/RMSE 3D/absolute error 3D/absolute relative error Depth Completion/RMSE Depth Estimation/Abs Rel Depth Estimation/Delta < 1.25 Depth Estimation/Delta < 1.25^2 Depth Estimation/Delta < 1.25^3 Depth Estimation/RMSE Depth Estimation/absolute error Depth Estimation/absolute relative error Semantic Segmentation/Test mIoU Semantic Segmentation/Validation mIoU

Statistics

Papers: 461
Benchmarks: 19

Links

Tasks

10-shot image generation 3D Depth Completion Depth Estimation Depth Prediction Monocular Depth Estimation Semantic Segmentation