Exploiting Diffusion Prior for Generalizable Dense Prediction

Figure 1. Generalized dense prediction. (left) We leverage the pre-trained text-to-image diffusion model [47] as a prior for various dense prediction tasks. (right) With only a small amount of labeled training data in a limited domain (i.e., 10K bedroom images with labels) for each task, our method performs favorably against SOTA predictors [5, 15, 26] on arbitrary images.