LED2-Net

Reported on 5 benchmarks across 5 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology2 results

3D ReconstructiononStanford2D3D Panoramic
3DIoU· 2021-04-01
83.77
best: 84.93 (DMH-Net)
LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Rendering arXiv:2104.00568
3DonStanford2D3D Panoramic
3DIoU· 2021-04-01
83.77
best: 84.93 (DMH-Net)
LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Rendering arXiv:2104.00568

Computer Vision2 results

Scene ParsingonStanford2D3D Panoramic
3DIoU· 2021-04-01
83.77
best: 84.93 (DMH-Net)
LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Rendering arXiv:2104.00568
Scene UnderstandingonStanford2D3D Panoramic
3DIoU· 2021-04-01
83.77
best: 84.93 (DMH-Net)
LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Rendering arXiv:2104.00568

Audio1 result

2D Semantic SegmentationonStanford2D3D Panoramic
3DIoU· 2021-04-01
83.77
best: 84.93 (DMH-Net)
LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Rendering arXiv:2104.00568