PanDORA: Casual HDR Radiance Acquisition for Indoor Scenes
This addresses the challenge of efficient HDR acquisition for indoor environments in computer vision, offering a scalable solution, though it is incremental as it builds on NeRF and exposure bracketing techniques.
The paper tackles the problem of capturing high dynamic range (HDR) radiance for indoor scenes in novel view synthesis, which is limited by low dynamic range images, by introducing PanDORA, a system that uses two 360° cameras and a two-stage NeRF-based algorithm to generate non-saturated HDR radiance maps, achieving superior visual fidelity compared to existing methods on a novel real indoor dataset.
Most novel view synthesis methods-including Neural Radiance Fields (NeRF)-struggle to capture the true high dynamic range (HDR) radiance of scenes. This is primarily due to their dependence on low dynamic range (LDR) images from conventional cameras. Exposure bracketing techniques aim to address this challenge, but they introduce a considerable time burden during the acquisition process. In this work, we introduce PanDORA: PANoramic Dual-Observer Radiance Acquisition, a system designed for the casual, high quality HDR capture of indoor environments. Our approach uses two 360° cameras mounted on a portable monopod to simultaneously record two panoramic 360° videos: one with standard exposure and another at fast shutter speed. The resulting video data is processed by a proposed two-stage NeRF-based algorithm, including an algorithm for the fine alignment of the fast- and well-exposed frames, generating non-saturated HDR radiance maps. Compared to existing methods on a novel dataset of real indoor scenes captured with our apparatus and including HDR ground truth lighting, PanDORA achieves superior visual fidelity and provides a scalable solution for capturing real environments in HDR.