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

2026-03-20

AI Summary

This work addresses the high computational cost of high-resolution NeRF rendering and the inability of existing 2D super-resolution methods to preserve multi-view consistency. To this end, we propose the first generalizable, 3D-aware NeRF super-resolution framework based on Neural Graphics Primitives (NGP), which jointly models 3D coordinates and learned local texture tokens to directly reconstruct a high-resolution radiance field from low-resolution posed images. Our method requires no per-scene optimization, external high-resolution references, or post-hoc 2D upsampling, yet efficiently recovers high-frequency details while maintaining view consistency on novel scenes. Experiments demonstrate that our approach significantly outperforms existing NeRF super-resolution techniques across multiple datasets, achieving state-of-the-art performance in both reconstruction quality and inference efficiency.

Technology Category

• Computer Vision: 3D Computer Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

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.

Problem

• Neural Radiance Fields
• Super-Resolution
• Multi-view Consistency
• Generalizable Rendering
• High-Resolution Novel View Synthesis

Innovation

• Neural Radiance Fields
• Super-Resolution
• Neural Graphics Primitives
• Generalizable
• View-Consistent