Deep Learning on Object-centric 3D Neural Fields

In recent years, Neural Fields ( NF s) have emerged as an effective tool for encoding diverse continuous signals such as images, videos, audio, and 3D shapes. When applied to 3D data, NF s offer a solution to the fragmentation and limitations associated with prevalent discrete representations. However, given that NF s are essentially neural networks, it remains unclear whether and how they can be seamlessly integrated into deep learning pipelines for solving downstream tasks. This paper addresses this research problem and introduces nf2vec , a framework capable of generating a compact latent representation for an input NF in a single inference pass. We demonstrate that nf2vec effectively embeds 3D objects represented by the input NF s and showcase how the resulting embeddings can be employed in deep learning pipelines to successfully address various tasks, all while processing exclusively NF s. We test this framework on several NF s used to represent 3D surfaces, such as unsigned/signed distance and occupancy fields. Moreover, we demonstrate the effectiveness of our approach with more complex NF s that encompass both geometry and appearance of 3D objects such as neural radiance fields.