Unleashing Text-to-Image Diffusion Models for Visual Perception
Open paper
Benchmark
Model
Rank
Results
monocular-depth-estimation-on-nyu-depth-v2
VPD
#22
absolute relative error: 0.069
RMSE: 0.254
log 10: 0.030
…
referring-expression-segmentation-on-refcoco-val
VPD
#23
Overall IoU: 73.25
Rank counts only results with a code link.