HDR-NeRF: High Dynamic Range Neural Radiance Fields

TL;DR

HDR-NeRF introduces a novel method to recover high dynamic range radiance fields from low dynamic range images with different exposures, enabling the generation of HDR and LDR views and improving scene radiance modeling.

Contribution

The paper proposes modeling the physical imaging process with implicit functions for radiance and tone mapping, allowing HDR reconstruction from LDR images using neural radiance fields.

Findings

Accurately recovers HDR radiance fields from LDR images.

Generates both HDR and LDR views under different exposures.

Validated on synthetic and real-world scenes.

Abstract

We present High Dynamic Range Neural Radiance Fields (HDR-NeRF) to recover an HDR radiance field from a set of low dynamic range (LDR) views with different exposures. Using the HDR-NeRF, we are able to generate both novel HDR views and novel LDR views under different exposures. The key to our method is to model the physical imaging process, which dictates that the radiance of a scene point transforms to a pixel value in the LDR image with two implicit functions: a radiance field and a tone mapper. The radiance field encodes the scene radiance (values vary from 0 to +infty), which outputs the density and radiance of a ray by giving corresponding ray origin and ray direction. The tone mapper models the mapping process that a ray hitting on the camera sensor becomes a pixel value. The color of the ray is predicted by feeding the radiance and the corresponding exposure time into the tone mapper. We use the classic volume rendering technique to project the output radiance, colors, and densities into HDR and LDR images, while only the input LDR images are used as the supervision. We collect a new forward-facing HDR dataset to evaluate the proposed method. Experimental results on synthetic and real-world scenes validate that our method can not only accurately control the exposures of synthesized views but also render views with a high dynamic range.