DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservation

… Batman" "… Joker" "a photo of a face" "a photo of a bear statue" "… Einstein" "… grizzly bear" "… Hulk" "… Storm Trooper" "… the Tolkien Elf" "… panda" "a photo of a campsite" "… just snowed" "a photo of a farm" "… autumn" "… polar bear" "… a mustache" * Equal contribution See more extensive results on our project page: https://dream-catalyst.github.io . Published as a conference paper at ICLR 2025 approximately 23 times faster than current state-of-the-art NeRF editing methods, and (2) a high-quality mode that produces superior results about 8 times faster than these methods. Notably, our high-quality mode outperforms current state-ofthe-art NeRF editing methods in terms of both speed and quality. DreamCatalyst also surpasses the state-of-the-art 3D Gaussian Splatting (3DGS) editing methods, establishing itself as an effective and model-agnostic 3D editing solution.