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

TL;DR

I2-NeRF introduces a physically-grounded neural radiance field framework that improves 3D perception under media degradation by modeling complex media interactions and achieving near-uniform sampling for better isometry and isotropy.

Contribution

It proposes a novel media-aware radiance formulation and a reverse-stratified sampling strategy to enhance NeRF's physical realism and metric perception in degraded media environments.

Findings

Significantly improves reconstruction fidelity.

Enhances physical plausibility in media environments.

Enables estimation of medium properties like water depth.

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.