| --- |
| license: apache-2.0 |
| tags: |
| - diffusion |
| - image-to-image |
| - depth-estimation |
| - optical-flow |
| - amodal-segmentation |
| --- |
| |
| # Scaling Properties of Diffusion Models for Perceptual Tasks |
|
|
| ### CVPR 2025 |
|
|
| **Rahul Ravishankar\*, Zeeshan Patel\*, Jathushan Rajasegaran, Jitendra Malik** |
|
|
| [[Paper](https://arxiv.org/abs/2411.08034)] 路 [[Project Page](https://scaling-diffusion-perception.github.io/)] |
|
|
|
|
| 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. |
|
|
|
|
| ## Getting started |
|
|
| You can download our DiT-MoE Generalist model [here](https://huggingface.co/zeeshanp/scaling_diffusion_perception/blob/main/dit_moe_generalist.pt). Please see instructions on how to use our model in the [GitHub README](https://github.com/scaling-diffusion-perception/scaling-diffusion-perception)路 |
