Recent advances in Neural Fields mostly rely on developing task-specific supervision which often complicates the models. Rather than developing hard-to-combine and specific modules, another approach generally overlooked is to directly inject generic priors on the scene representation (also called inductive biases) into the NeRF architecture. Based on this idea, we propose the RING-NeRF architecture which includes two inductive biases : a continuous multi-scale representation of the scene and an invariance of the decoder's latent space over spatial and scale domains. We also design a single reconstruction process that takes advantage of those inductive biases and experimentally demonstrates on-par performances in terms of quality with dedicated architecture on multiple tasks (anti-aliasing, few view reconstruction, SDF reconstruction without scene-specific initialization) while being more efficient. Moreover, RING-NeRF has the distinctive ability to dynamically increase the resolution of the model, opening the way to adaptive reconstruction.

翻译：近期神经场领域的进展主要依赖于开发任务特定监督方法，这往往导致模型复杂度增加。相较于设计难以融合的专用模块，另一种常被忽视的思路是直接将场景表示中的通用先验知识（即归纳偏置）注入NeRF架构。基于这一思想，我们提出RING-NeRF架构，其中包含两种归纳偏置：场景的连续多尺度表示，以及解码器隐空间在空间域与尺度域上的不变性。我们还设计了一个能充分利用这些归纳偏置的单次重建流程，实验证明其在多项任务（抗锯齿、少视角重建、无需场景初始化的有符号距离场重建）中均能达到与专用架构相当的重建质量，同时具有更高效率。此外，RING-NeRF具备动态提升模型分辨率的独特能力，为自适应重建开辟了新途径。