HyperFields: Towards Zero-Shot Generation of NeRFs from Text
This addresses the challenge of efficient 3D scene generation from text for applications in computer vision and graphics, representing a novel method rather than an incremental improvement.
The paper tackles the problem of generating Neural Radiance Fields (NeRFs) from text, achieving zero-shot or few-shot synthesis with a single forward pass and optional fine-tuning, resulting in 5 to 10 times faster scene generation compared to existing methods.
We introduce HyperFields, a method for generating text-conditioned Neural Radiance Fields (NeRFs) with a single forward pass and (optionally) some fine-tuning. Key to our approach are: (i) a dynamic hypernetwork, which learns a smooth mapping from text token embeddings to the space of NeRFs; (ii) NeRF distillation training, which distills scenes encoded in individual NeRFs into one dynamic hypernetwork. These techniques enable a single network to fit over a hundred unique scenes. We further demonstrate that HyperFields learns a more general map between text and NeRFs, and consequently is capable of predicting novel in-distribution and out-of-distribution scenes -- either zero-shot or with a few finetuning steps. Finetuning HyperFields benefits from accelerated convergence thanks to the learned general map, and is capable of synthesizing novel scenes 5 to 10 times faster than existing neural optimization-based methods. Our ablation experiments show that both the dynamic architecture and NeRF distillation are critical to the expressivity of HyperFields.