TransDepth (AGD+ ViT)

Reported on 2 benchmarks across 2 tasks · 1 paper

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

Computer Vision1 result

Depth EstimationonNYU-Depth V2
RMS· 2021-03-22
0.365
best: 0.792 (PAD-Net)
Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction arXiv:2103.12091

Methodology1 result

3DonNYU-Depth V2
RMS· 2021-03-22
0.365
best: 0.792 (PAD-Net)
Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction arXiv:2103.12091