I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions

2025-10-25

AI Summary

Existing NeRF methods suffer from non-uniform 3D spatial sampling and lack a unified physically grounded modeling framework for medium-induced degradations—such as underwater imaging, haze, and low-light conditions—leading to distorted radiance fields and inaccurate estimation of medium properties (e.g., water depth). To address this, we propose a reverse hierarchical upsampling strategy and, for the first time, integrate the Beer–Lambert law into the NeRF framework, establishing a unified physically based radiative degradation model that jointly optimizes emission, absorption, and anisotropic scattering. Leveraging differentiable rendering coupled with physics-informed light transport simulation, our approach enables isotropic metric-aware reconstruction and joint estimation of medium parameters. Evaluated on real-world datasets, our method significantly improves 3D reconstruction fidelity and physical consistency, enabling high-fidelity scene reconstruction and accurate inversion of critical physical quantities—including water depth.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Search and Optimization: Sampling/Simulation-based Search
• Reasoning under Uncertainty: Relational Probabilistic Models

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: Graph embeddings and representation learning for Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Participating in efforts to endow generative AI with the 3D physical world perception, we propose I2-NeRF, a novel neural radiance field framework that enhances isometric and isotropic metric perception under media degradation. While existing NeRF models predominantly rely on object-centric sampling, I2-NeRF introduces a reverse-stratified upsampling strategy to achieve near-uniform sampling across 3D space, thereby preserving isometry. We further present a general radiative formulation for media degradation that unifies emission, absorption, and scattering into a particle model governed by the Beer-Lambert attenuation law. By composing the direct and media-induced in-scatter radiance, this formulation extends naturally to complex media environments such as underwater, haze, and even low-light scenes. By treating light propagation uniformly in both vertical and horizontal directions, I2-NeRF enables isotropic metric perception and can even estimate medium properties such as water depth. Experiments on real-world datasets demonstrate that our method significantly improves both reconstruction fidelity and physical plausibility compared to existing approaches.

Problem

• Enhancing 3D metric perception under media degradation
• Achieving uniform sampling in neural radiance fields
• Modeling light propagation in complex media environments

Innovation

• Reverse-stratified upsampling for uniform 3D sampling
• Radiative formulation unifying emission, absorption, scattering
• Isotropic light propagation enabling medium property estimation