Generalizable NGP-SR: Generalizable Neural Radiance Fields Super-Resolution via Neural Graph Primitives

TL;DR

This paper introduces a 3D-aware super-resolution framework called Generalizable NGP-SR that reconstructs high-resolution radiance fields from low-resolution images, ensuring view consistency and generalizability across unseen scenes.

Contribution

The proposed NGP-SR method is the first to achieve generalizable, 3D-aware super-resolution of neural radiance fields without scene-specific training or external references.

Findings

Improves reconstruction quality over prior methods

Enhances runtime efficiency for high-resolution synthesis

Maintains multi-view consistency without external HR references

Abstract

Neural Radiance Fields (NeRF) achieve photorealistic novel view synthesis but become costly when high-resolution (HR) rendering is required, as HR outputs demand dense sampling and higher-capacity models. Moreover, naively super-resolving per-view renderings in 2D often breaks multi-view consistency. We propose Generalizable NGP-SR, a 3D-aware super-resolution framework that reconstructs an HR radiance field directly from low-resolution (LR) posed images. Built on Neural Graphics Primitives (NGP), NGP-SR conditions radiance prediction on 3D coordinates and learned local texture tokens, enabling recovery of high-frequency details within the radiance field and producing view-consistent HR novel views without external HR references or post-hoc 2D upsampling. Importantly, our model is generalizable: once trained, it can be applied to unseen scenes and rendered from novel viewpoints without per-scene optimization. Experiments on multiple datasets show that NGP-SR consistently improves both reconstruction quality and runtime efficiency over prior NeRF-based super-resolution methods, offering a practical solution for scalable high-resolution novel view synthesis.