Daniel Winter1,2 Matan Cohen1 Shlomi Fruchter1 Yael Pritch1 Alex Rav‑Acha1 Yedid Hoshen1,2
1Google Research 2The Hebrew University of Jerusalem
ECCV 2024
Our object removal model effectively eliminates objects and their effects on the scene from images. Despite being trained on a relatively small counterfactual dataset captured in controlled environments, the model demonstrates remarkable generalization to diverse scenarios, seamlessly removing large objects.
By training first on a large synthetic dataset created with the object removal model, and then on a high-quality dataset, our object insertion model can accurately model how an object affects its environment, achieving realistic results.
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
![]() ![]() ![]() ![]() |
Utilizing both our object removal and insertion models, we can seamlessly move objects within an image. This involves removing them from their original position and re-inserting them elsewhere, resulting in realistic transformations.
![]() ![]() ![]() ![]() ![]() ![]() | ![]() ![]() ![]() ![]() ![]() ![]() |
![]() ![]() ![]() ![]() ![]() ![]() |
Click on any image to see results
We thank owners of images on this site (link for attributions) for sharing their valuable assets.