Casual Indoor HDR Radiance Capture from Omnidirectional Images

British Machine Vision Conference 2022

Pulkit Gera¹, Mohammad Reza Karimi Dastjerdi², Charles Renaud², P J Narayanan¹ Jean-François Lalonde²

¹CVIT, IIIT Hyderabad

²Université Laval

---

[Project page] [Paper] [Video] [Data] [bibtex]

---

Abstract
We present PanoHDR-NeRF, a novel pipeline to casually capture a plausible full HDR radiance field of a large indoor scene without elaborate setups or complex capture protocols. First, a user captures a low dynamic range (LDR) omnidirectional video of the scene by freely waving an off-the-shelf camera around the scene. Then, an LDR2HDR network uplifts the captured LDR frames to HDR, subsequently used to train a tailored NeRF++ model. The resulting PanoHDR-NeRF pipeline can estimate full HDR panoramas from any location of the scene. Through experiments on a novel test dataset of a variety of real scenes with the ground truth HDR radiance captured at locations not seen during training, we show that PanoHDR-NeRF predicts plausible radiance from any scene point. We also show that the HDR images produced by PanoHDR-NeRF can synthesize correct lighting effects, enabling the augmentation of indoor scenes with synthetic objects that are lit correctly.

LDR2HDR

Instructions for running LDR2HDR module are present in LANet directory.

PanoHDR-NeRF

Instructions for running and installing NeRF module is present in PanoHDR_NeRF directory.