QNeRF: Neural Radiance Fields on a Simulated Gate-Based Quantum Computer

TL;DR

QNeRF introduces a hybrid quantum-classical model for novel-view synthesis that leverages quantum circuits to create more compact models, matching or surpassing classical NeRF performance with fewer parameters.

Contribution

This work presents the first hybrid quantum-classical neural radiance field model, QNeRF, which uses quantum circuits for efficient 3D scene representation from 2D images.

Findings

QNeRF matches or outperforms classical NeRF with fewer parameters.

Quantum encoding enhances model compactness and representational capacity.

Dual-Branch QNeRF improves scalability and hardware compatibility.

Abstract

Recently, Quantum Visual Fields (QVFs) have shown promising improvements in model compactness and convergence speed for learning the provided 2D or 3D signals. Meanwhile, novel-view synthesis has seen major advances with Neural Radiance Fields (NeRFs), where models learn a compact representation from 2D images to render 3D scenes, albeit at the cost of larger models and intensive training. In this work, we extend the approach of QVFs by introducing QNeRF, the first hybrid quantum-classical model designed for novel-view synthesis from 2D images. QNeRF leverages parameterised quantum circuits to encode spatial and view-dependent information via quantum superposition and entanglement, resulting in more compact models compared to the classical counterpart. We present two architectural variants. Full QNeRF maximally exploits all quantum amplitudes to enhance representational capabilities. In contrast, Dual-Branch QNeRF introduces a task-informed inductive bias by branching spatial and view-dependent quantum state preparations, drastically reducing the complexity of this operation and ensuring scalability and potential hardware compatibility. Our experiments demonstrate that -- when trained on images of moderate resolution -- QNeRF matches or outperforms classical NeRF baselines while using less than half the number of parameters. These results suggest that quantum machine learning can serve as a competitive alternative for continuous signal representation in mid-level tasks in computer vision, such as 3D representation learning from 2D observations.