Scaling Properties of Diffusion Models for Perceptual Tasks

Rahul Ravishankar, Zeeshan Patel, Jathushan Rajasegaran, Jitendra Malik

Scaling Properties of Diffusion Models for Perceptual Tasks: 13 upvotes on Hugging Face Daily Papers, #5 of 8 papers on 2024-11-13. Day-by-day upvote history.

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 segmentation under image-to-image translation, and show how diffusion models benefit from scaling training and test-time compute for these perception tasks. Through a careful analysis of these scaling behaviors, we present various techniques to efficiently train diffusion models for visual perception tasks. Our models achieve improved or comparable performance to state-of-the-art methods using significantly less data and compute. To use our code and models, see https://scaling-diffusion-perception.github.io .

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.