NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors

1 code implementation • CVPR 2023 • Congyue Deng, Chiyu "Max'' Jiang, Charles R. Qi, Xinchen Yan, Yin Zhou, Leonidas Guibas, Dragomir Anguelov

Formulating single-view reconstruction as an image-conditioned 3D generation problem, we optimize the NeRF representations by minimizing a diffusion loss on its arbitrary view renderings with a pretrained image diffusion model under the input-view constraint.

3D Generation 3D Reconstruction