Pix2NeRF: Unsupervised Conditional $\pi$-GAN for Single Image to Neural Radiance Fields Translation

We propose a pipeline to generate Neural Radiance Fields (NeRF) of an object or a scene of a specific class, conditioned on a single input image. This is a challenging task, as training NeRF requires multiple views of the same scene, coupled with corresponding poses, which are hard to obtain. Our method is based on <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\pi$</tex> -GAN, a generative model for unconditional 3D-aware image synthesis, which maps random latent codes to radiance fields of a class of objects. We jointly optimize (1) the <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\pi$</tex> -GAN objective to utilize its high-fidelity 3D-aware generation and (2) a carefully designed reconstruction objective. The latter includes an encoder coupled with <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\pi$</tex> -GAN generator to form an autoencoder. Unlike previous few-shot NeRF approaches, our pipeline is unsupervised, capable of being trained with independent images without 3D, multi-view, or pose supervision. Applications of our pipeline include 3d avatar generation, object-centric novel view synthesis with a single input image, and 3d-aware super-resolution, to name a few.