paper-with-me

Matterport3D

홈페이지 · 논문 461편

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

3DRGB-D

벤치마크

Semantic Segmentation on Matterport3D 결과 8개
Depth Completion on Matterport3D 결과 2개
Depth Estimation on Matterport3D 결과 2개
Monocular Depth Estimation on Matterport3D 결과 2개