flâneur

[2401.05335] InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenes

arxiv.org · 261 words · saved by 1 readers

If you have code to share with the arXiv community, please submit it here to benefit all researchers & engineers. We couldn't find an implemetation for this paper yet. Create a project to share your data, models, code and experiments with the arXiv community. No Replicate demos found for this article. You can add one here. No Spaces demos found for this article. You can add one here. No matching paper found See related papers to: InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenes arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Sta

View PDF HTML (experimental) Abstract:We introduce InseRF, a novel method for generative object insertion in the NeRF reconstructions of 3D scenes. Based on a user-provided textual description and a 2D bounding box in a reference viewpoint, InseRF generates new objects in 3D scenes. Recently, methods for 3D scene editing have been profoundly transformed, owing to the use of strong priors of text-to-image diffusion models in 3D generative modeling. Existing methods are mostly effective in editing 3D scenes via style and appearance changes or removing existing objects. Generating new objects,…

saved by

related reading