Harnessing Diffusion Models for Visual Perception with Meta Prompts

Benchmark Model Rank Results
semantic-segmentation-on-cityscapes-testMetaPrompt-SD#2Mean IoU (class): 86.2
semantic-segmentation-on-cityscapes-valMetaPrompt-SD#3mIoU: 87.1
monocular-depth-estimation-on-kitti-eigen-splitMetaPrompt-SD#10absolute relative error: 0.047RMSE: 1.928Sq Rel: 0.125…
human-pose-keypoint-estimation-on-coco-val2017MetaPrompt-SD#14AP: 79.0
monocular-depth-estimation-on-nyu-depth-v2MetaPrompt-SD#17absolute relative error: 0.061RMSE: 0.223log 10: 0.027…
semantic-segmentation-on-ade20kMetaPrompt-SD#38Validation mIoU: 56.8