Quantum Implicit Neural Representations for 3D Scene Reconstruction and Novel View Synthesis

2025-12-14

AI Summary

Traditional implicit neural representations (INRs) suffer from spectral bias, hindering faithful modeling of high-frequency details in 3D scenes. To address this, we propose Q-NeRF—the first quantum-classical hybrid neural radiance field framework—replacing NeRF’s density and radiance prediction modules with a parametrized quantum implicit representation network (QIREN). Leveraging parameterized quantum circuits, QIREN intrinsically supports Fourier-basis expansion, effectively mitigating the spectral bias inherent in multi-layer perceptrons (MLPs). Integrated into the NeRFacto architecture, Q-NeRF incorporates volumetric rendering, multi-view geometric constraints, and pose optimization, enabling efficient training and inference under limited-qubit simulation. Experiments on indoor multi-view datasets demonstrate that Q-NeRF achieves PSNR, SSIM, and LPIPS scores comparable to classical baselines, while significantly improving reconstruction fidelity for view-dependent appearance and fine-grained structural details—validating the feasibility of resource-efficient quantum enhancement for neural rendering.

Technology Category

• Machine Learning: Quantum Machine Learning
• Knowledge Representation and Reasoning: Qualitative Reasoning
• Computer Vision: 3D Computer Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Implicit neural representations (INRs) have become a powerful paradigm for continuous signal modeling and 3D scene reconstruction, yet classical networks suffer from a well-known spectral bias that limits their ability to capture high-frequency details. Quantum Implicit Representation Networks (QIREN) mitigate this limitation by employing parameterized quantum circuits with inherent Fourier structures, enabling compact and expressive frequency modeling beyond classical MLPs. In this paper, we present Quantum Neural Radiance Fields (Q-NeRF), the first hybrid quantum-classical framework for neural radiance field rendering. Q-NeRF integrates QIREN modules into the Nerfacto backbone, preserving its efficient sampling, pose refinement, and volumetric rendering strategies while replacing selected density and radiance prediction components with quantum-enhanced counterparts. We systematically evaluate three hybrid configurations on standard multi-view indoor datasets, comparing them to classical baselines using PSNR, SSIM, and LPIPS metrics. Results show that hybrid quantum-classical models achieve competitive reconstruction quality under limited computational resources, with quantum modules particularly effective in representing fine-scale, view-dependent appearance. Although current implementations rely on quantum circuit simulators constrained to few-qubit regimes, the results highlight the potential of quantum encodings to alleviate spectral bias in implicit representations. Q-NeRF provides a foundational step toward scalable quantum-enabled 3D scene reconstruction and a baseline for future quantum neural rendering research.

Problem

• Overcoming spectral bias in implicit neural representations for 3D scenes
• Enhancing high-frequency detail capture in neural radiance field rendering
• Integrating quantum circuits to improve view-dependent appearance modeling

Innovation

• Quantum circuits with Fourier structures for frequency modeling
• Hybrid quantum-classical framework for neural radiance fields
• Quantum modules enhance fine-scale view-dependent appearance representation