Speaking of folks with whom I’ve somehow had the honor of working, some of my old teammates from Google have unveiled ObjectDrop. Check out this video & thread:
Google presents ObjectDrop
Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion
Diffusion models have revolutionized image editing but often generate images that violate physical laws, particularly the effects of objects on the scene, e.g., pic.twitter.com/j7TMadRhxo
— AK (@_akhaliq) March 28, 2024
A bit more detail, from the project site:
Diffusion models have revolutionized image editing but often generate images that violate physical laws, particularly the effects of objects on the scene, e.g., occlusions, shadows, and reflections. By analyzing the limitations of self-supervised approaches, we propose a practical solution centered on a counterfactual dataset.
Our method involves capturing a scene before and after removing a single object, while minimizing other changes. By fine-tuning a diffusion model on this dataset, we are able to not only remove objects but also their effects on the scene. However, we find that applying this approach for photorealistic object insertion requires an impractically large dataset. To tackle this challenge, we propose bootstrap supervision; leveraging our object removal model trained on a small counterfactual dataset, we synthetically expand this dataset considerably.
Our approach significantly outperforms prior methods in photorealistic object removal and insertion, particularly at modeling the effects of objects on the scene.
