In this paper, we argue that iterative computation with diffusion models offers a powerful paradigm for not only generation but also visual perception tasks. We unify tasks such as depth estimation, optical flow, and amodal segmentation under the framework of image-to-image translation, and show how diffusion models benefit from scaling training and test-time compute for these perceptual tasks. Through a careful analysis of these scaling properties, we formulate compute-optimal training and inference recipes to scale diffusion models for visual perception tasks. Our models achieve competitive performance to state-of-the-art methods using significantly less data and compute. To access our code and models, see https://scaling-diffusion-perception.github.io .
@article{arxiv.2411.08034,
title = {Scaling Properties of Diffusion Models for Perceptual Tasks},
author = {Rahul Ravishankar and Zeeshan Patel and Jathushan Rajasegaran and Jitendra Malik},
journal= {arXiv preprint arXiv:2411.08034},
year = {2024}
}