# Ambient-robust Inverse Rendering using Active RGB-NIR Imaging

Source: [Ambient-robust Inverse Rendering using Active RGB-NIR Imaging](<https://www.sota2.com/research/paper/6a191dbcdbd7150506f829f1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-30T05:00:11.986Z

Authors: Hoon-Gyu Chung, Jinnyeong Kim, Hyunwoo Kang, Seung-Hwan Baek

Published: 2026-05-28T17:13:41.000Z

## Abstract

Inverse rendering aims to reconstruct geometry and reflectance of objects from images. Despite recent progress, existing methods often produces inaccurate reconstructions that are sensitive to ambient illumination conditions. Here we introduce an ambient-robust inverse rendering method enabled by active RGB-NIR imaging. Our key insight is to leverage near-infrared (NIR) flash illumination-imperceptible to human observers-to obtain stable point-light shading that is largely invariant to ambient illumination. By using multi-view RGB images illuminated by ambient light and NIR images acquired with active NIR flash illumination, we reconstruct accurate geometry and reflectance by exploiting the complementary benefits of RGB and NIR images via a three-stage inverse rendering method. To enable dense multi-view acquisition, we develop an active imaging system equipped with a RGB-NIR camera and a NIR flash mounted on a mobile base. Using this system, we collect the first multi-view RGB-NIR inverse rendering dataset captured under multiple ambient illumination conditions. Experiments demonstrate that our method outperforms prior approaches, achieving accurate geometry and reflectance estimation across multiple ambient lighting scenarios.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [RGB Diffuse Albedo Estimation on Synthetic and Real-World Dataset](<https://www.sota2.com/research/sota/rgb-diffuse-albedo-estimation-on-synthetic-and-real-world-dataset.md>): RGB Diffuse Albedo Estimation; Synthetic and Real-World Dataset; PSNR: 27.89.

- [Roughness Estimation on Synthetic and Real-World Dataset](<https://www.sota2.com/research/sota/roughness-estimation-on-synthetic-and-real-world-dataset.md>): Roughness Estimation; Synthetic and Real-World Dataset; RMSE: 0.0713.

- [Surface Normal Estimation on Synthetic and Real-World Dataset](<https://www.sota2.com/research/sota/surface-normal-estimation-on-synthetic-and-real-world-dataset.md>): Surface Normal Estimation; Synthetic and Real-World Dataset; MAE: 7.73.

- [Relighting on Synthetic and Real-World Dataset](<https://www.sota2.com/research/sota/relighting-on-synthetic-and-real-world-dataset.md>): Relighting; Synthetic and Real-World Dataset; PSNR: 31.01.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.30250>)

[PDF](<https://arxiv.org/pdf/2605.30250.pdf>)