LatentEditor: Text Driven Local Editing of 3D Scenes

arXiv:2312.09313v3 Announce Type: replace
Abstract: While neural fields have made significant strides in view synthesis and scene reconstruction, editing them poses a formidable challenge due to their implicit encoding of geometry and texture information from multi-view inputs. In this paper, we introduce \textsc{LatentEditor}, an innovative framework designed to empower users with the ability to perform precise and locally controlled editing of neural fields using text prompts. Leveraging denoising diffusion models, we successfully embed real-world scenes into the latent space, resulting …

3d scenes abstract arxiv challenge cs.ai cs.cv editing encoding fields framework geometry information inputs paper synthesis text texture them type view