PanDORA: Casual HDR Radiance Acquisition of Indoor Scenes for Image-based Lighting

TL;DR

PanDORA is a fast, portable system that captures high-quality HDR radiance maps of indoor scenes using dual 360° cameras and a novel NeRF-based algorithm, improving realism in image-based lighting.

Contribution

It introduces a dual-camera setup and a self-calibrating NeRF pipeline for efficient, high-fidelity HDR radiance acquisition suitable for indoor scene lighting.

Findings

Outperforms existing methods in capturing scene radiance accurately.

Produces non-saturated HDR radiance fields for realistic rendering.

Demonstrates scalability and efficiency in real indoor environments.

Abstract

Most novel view synthesis methods -- including Neural Radiance Fields (NeRF) -- struggle to capture the high dynamic range (HDR) radiance required for realistic image-based lighting (IBL). This limitation stems from a reliance on low dynamic range (LDR) imagery, which fails to capture the intensity of light sources found in indoor environments. While exposure bracketing can recover this range, it is often too slow for practical, large-scale acquisition. In this work, we introduce PanDORA: PANoramic Dual-Observer Radiance Acquisition, a system specifically designed for the fast and affordable capture of high-quality HDR radiance maps for IBL. Our approach utilizes two 360{\deg} cameras mounted on a portable monopod to simultaneously record videos at different exposures. These videos are processed by our proposed two-stage NeRF-based algorithm featuring a novel self-calibrating pipeline to estimate camera parameters. This pipeline produces non-saturated HDR radiance fields that accurately capture the radiance of a scene. When evaluated on a new dataset of real indoor environments featuring HDR ground truth lighting, PanDORA demonstrates superior fidelity in reconstructing the peak intensities necessary for downstream rendering tasks, providing a scalable and efficient solution for capturing real-world IBLs.