GIRAFFE HD: A High-Resolution 3D-aware Generative Model

3D-aware generative models have shown that the introduction of 3D information can lead to more controllable image generation. In particular, the current state-of-the-art model GIRAFFE I j can control each object's rotation, translation, scale, and scene camera pose without corresponding supervision. However, GIRAFFE only operates well when the image resolution is low We propose GIRAFFE HD, a high-resolution 3D-aware generative model that inherits all of GIRAFFE's controllable features while generating high -quality, high -resolution images (5122 resolution and above). The key idea is to leverage a style based neural renderer, and to independently generate the foreground and background to force their disentanglement while imposing consistency constraints to stitch them together to composite a coherent final image. We demonstrate state-of-the-art 3D controllable high -resolution image generation on multiple natural image datasets.

Automated summary

3D-aware generative models have shown that introducing 3D information can lead to more controllable image generation. We propose GIRAFFE HD, a high-resolution 3D-aware generative model that inherits all the controllable features of GIRAFFE while generating high-quality, high-resolution images. The key idea is to leverage a style-based neural renderer to independently generate and stitch together foreground and background, resulting in coherent final images. We demonstrate state-of-the-art 3D controllable high-resolution image generation on multiple natural image datasets.