A Survey on Deep Generative 3D-aware Image Synthesis
It serves as a reference for researchers in computer vision by organizing rapid progress in a field that bridges 2D imagery and 3D reality, but it is incremental as a survey rather than presenting new methods.
This paper provides a comprehensive survey on deep generative 3D-aware image synthesis, which tackles the problem of generating high-fidelity, 3D-consistent images from 2D data without 3D supervision, summarizing hundreds of recent papers to introduce the field and stimulate future research.
Recent years have seen remarkable progress in deep learning powered visual content creation. This includes deep generative 3D-aware image synthesis, which produces high-idelity images in a 3D-consistent manner while simultaneously capturing compact surfaces of objects from pure image collections without the need for any 3D supervision, thus bridging the gap between 2D imagery and 3D reality. The ield of computer vision has been recently captivated by the task of deep generative 3D-aware image synthesis, with hundreds of papers appearing in top-tier journals and conferences over the past few years (mainly the past two years), but there lacks a comprehensive survey of this remarkable and swift progress. Our survey aims to introduce new researchers to this topic, provide a useful reference for related works, and stimulate future research directions through our discussion section. Apart from the presented papers, we aim to constantly update the latest relevant papers along with corresponding implementations at https://weihaox.github.io/3D-aware-Gen.