UC Berkeley’s Instruct-NeRF2NeRF Edits 3D Scenes With Text Instructions

In the new paper Instruct-NeRF2NeRF: Editing 3D Scenes With Instructions, a UC Berkeley research team presents Instruct-NeRF2NeRF, an approach for editing 3D NeRF scenes through natural language text instructions. The proposed method can edit large-scale, real-world 3D scenes with improved ease of use and realism.

3d reconstruction 3d scenes ai artificial intelligence computer vision & graphics deep-neural-networks editing language machine learning machine learning & data science ml natural natural language nerf neural radiance fields paper research research team scale team technology text through uc berkeley world